CN111950194A - Newton momentum-based distributed acceleration composite optimization method and system - Google Patents
Newton momentum-based distributed acceleration composite optimization method and system Download PDFInfo
- Publication number
- CN111950194A CN111950194A CN202010709580.7A CN202010709580A CN111950194A CN 111950194 A CN111950194 A CN 111950194A CN 202010709580 A CN202010709580 A CN 202010709580A CN 111950194 A CN111950194 A CN 111950194A
- Authority
- CN
- China
- Prior art keywords
- agent
- neighbor
- local
- agents
- momentum
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses a Newton momentum-based distributed acceleration composite optimization method and system, which are characterized in that on the basis that a plurality of intelligent agents are connected into a non-directional network, a smooth structure and a non-smooth structure are combined to establish an objective function, so that the coverage range of the processed problem is wider, the established model is more accurate, the problem can be converged to a global optimal solution at a linear speed, the convergence speed is higher than that of a similar method by introducing a momentum acceleration item and a gradient tracking item, and the processing speed of large-scale intelligent automation equipment data can be effectively improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a Newton momentum-based distributed acceleration composite optimization method and system.
Background
Some optimization problems need to be solved in the fields of machine learning, statistical learning, unmanned aerial vehicle formation navigation, non-inductive sensor networks and the like, and the problems can be solved only through a single intelligent body when the problems are simpler. However, as information technology is continuously developed, in order to obtain more accurate solutions, the size of data to be considered and processed is larger and more accurate problem models need to be established, and the problem models are no longer simple smooth functions capable of representing problems, and may involve problems in a non-smooth form.
Considering that the existing computer has limited computing resources, a single agent cannot easily deal with the optimization problem of the large-scale compound form (smooth + non-smooth), so that the data processing speed of a large amount of intelligent automation equipment is slow.
Disclosure of Invention
The invention aims to solve the technical problem of the prior art, provides a Newton momentum-based distributed acceleration composite optimization method and system, and can effectively improve the data processing speed of large-scale intelligent automation equipment.
The technical scheme for solving the technical problems is as follows: a Newton momentum-based distributed acceleration composite optimization method comprises the following steps:
s1, connecting a plurality of agents into a non-directional communication network, and establishing an objective function combining a smooth structure and a non-smooth structure based on the agents:
wherein the content of the first and second substances,is a smooth local objective function known only to agent i,is a non-smooth local function known only to agent i,is the set of feasible solutions, m is the number of agents;
s2, each agent calculates its own local estimation value and sends it to the first neighbor agent, the first neighbor agent is the neighbor agent corresponding to the agent, the neighbor agents are the agents directly communicating between two agents, and each is the neighbor agent;
s3, the first neighbor agent calculates momentum acceleration item according to the received local estimation value and sends the momentum acceleration item to a second neighbor agent, and the second neighbor agent is the neighbor agent of the first neighbor agent;
s4, the second neighbor agent calculates a gradient tracking item according to the momentum acceleration item and sends the gradient tracking item to a third neighbor agent, and the third neighbor agent is an agent of the second neighbor agent;
s5, loop S2 to S4, and terminate the loop until a preset condition is met.
The method has the advantages that on the basis that a plurality of intelligent agents are connected into a non-directional network, the coverage range of the processed problems is wider by establishing the target function combining the smooth structure and the non-smooth structure, the established model is more accurate, the problem can be converged to the global optimal solution at a linear speed, the convergence speed is higher than that of a similar method by introducing the momentum acceleration item and the gradient tracking item, and the processing speed of large-scale intelligent automatic equipment data can be effectively improved.
Further, the calculation process of the local estimation in S2 is:
s201, each agent calculates local optimal solution of each agentThe calculation formula is as follows:
s202, calculating the local estimation value of the local optimal solution according to the local optimal solutionThe calculation formula is as follows:
wherein the content of the first and second substances,is thatIn the form of a continuous convex approximation of (a), is fiIn thatIs a positive constant step.
The method has the advantages that the variable is updated instead of the target function by using the distributed optimization strategy and utilizing the continuous convex approximation replacement of the target function, so that the method can still solve the fixed point for the target problem when the target problem is not convex, and can converge to the global optimal solution at a linear speed for the problem which can be modeled as the convex function when the introduced step length alpha is positive and smaller than a given upper bound.
Further, the calculation process of the momentum acceleration term in S3 is:
s301, carrying out weighted average on the local estimation values to obtain local average estimation valuesThe calculation formula is as follows:
s302, estimating according to the local averageCalculating the momentum acceleration term according to the following calculation formula:
The method has the advantages that the Newton momentum method is used for calculating the gradient in the steps S301 and S302, and the method has the advantages that under the condition that the updating direction is the same as the previous moment, the convergence speed can be accelerated to a certain extent, the updating direction of the gradient is adjusted, the stability of the distributed optimization method is improved, and the time overhead for solving the global optimal solution is reduced. The similar method also has a common momentum method, but the common momentum method is easy to have the condition of large fluctuation of variable values in the iteration process, and the system is unstable.
Further, the specific calculation formula of the gradient tracking term in S4 is as follows:
The beneficial effect of adopting the above further scheme is that by carrying out gradient tracing, the local agent can also trace the global gradient value, and the situation that the agent falls into solving the local optimal solution because the agent can only master the local information is avoided. Further, w isijThe value rule is as follows:
defining an undirected graphWhereinIs a set of agents that are intelligent agents,is a set of edges that are to be considered,is a weighted adjacency matrix in which the weights w for the edges (i, j)ijThe following conditions are satisfied: if (i, j) ∈ then wij> 0, otherwise wij=0,Wherein d isiIs the number of neighbor agents for agent i.
A Newton momentum-based distributed acceleration composite optimization system comprises an objective function establishing module and a plurality of intelligent agents which are connected into a non-directional communication network;
the objective function establishing module is used for establishing an objective function combining a smooth structure and a non-smooth structure according to the plurality of agents:
wherein the content of the first and second substances,is a smooth local objective function known only to agent i,is a non-smooth local function known only to agent i,is the set of feasible solutions, m is the number of agents;
the intelligent agents are used for calculating local estimation values of the intelligent agents and sending the local estimation values to a first neighbor intelligent agent, the first neighbor intelligent agent is a neighbor intelligent agent corresponding to the intelligent agent, the neighbor intelligent agents are intelligent agents which directly communicate between the two intelligent agents, and the neighbor intelligent agents are neighbor intelligent agents;
the first neighbor agent is used for calculating momentum acceleration items according to the received local estimation values and sending the momentum acceleration items to a second neighbor agent, and the second neighbor agent is a neighbor agent of the first neighbor agent;
the second neighbor agent is used for calculating a gradient tracking item according to the momentum acceleration item and sending the gradient tracking item to a third neighbor agent, and the third neighbor agent is an agent of the second neighbor agent;
the plurality of agents are further configured to loop the local estimates, the momentum acceleration term, the gradient tracking term until a predetermined condition is met and terminate the loop.
Further, the calculation process of the local estimation is as follows:
s201, each agent calculates local optimal solution of each agentThe calculation formula is as follows
S202, calculating the local estimation value of the local optimal solution according to the local optimal solutionThe calculation formula is as follows:
wherein the content of the first and second substances,is thatIn the form of a continuous convex approximation of (a), is fiIn thatIs a positive constant step.
The method has the advantages that on the basis that a plurality of intelligent agents are connected into a non-directional network, the coverage range of the processed problems is wider by establishing the target function combining the smooth structure and the non-smooth structure, the established model is more accurate, the problem can be converged to the global optimal solution at a linear speed, the convergence speed is higher than that of a similar method by introducing the momentum acceleration item and the gradient tracking item, and the processing speed of large-scale intelligent automatic equipment data can be effectively improved.
Further, the calculation process of the momentum acceleration term is as follows:
s301, carrying out weighted average on the local estimation values to obtain local average estimation valuesThe calculation formula is as follows:
s302, estimating according to the local averageCalculating the momentum acceleration term according to the following calculation formula:
The method has the advantages that the variable is updated instead of the target function by using the distributed optimization strategy and utilizing the continuous convex approximation replacement of the target function, so that the method can still solve the fixed point for the target problem when the target problem is not convex, and can converge to the global optimal solution at a linear speed for the problem which can be modeled as the convex function when the introduced step length alpha is positive and smaller than a given upper bound.
Further, the specific calculation formula of the gradient tracking term is as follows:
The beneficial effect of adopting the above further scheme is that by carrying out gradient tracing, the local agent can also trace the global gradient value, and the situation that the agent falls into solving the local optimal solution because the agent can only master the local information is avoided.
Further, w isijThe value rule is as follows:
defining an undirected graphWhereinIs a set of agents that are intelligent agents,is a set of edges that are to be considered,is a weighted adjacency matrix in which the weights w for the edges (i, j)ijThe following conditions are satisfied: if (i, j) ∈ then wij> 0, otherwise wij=0,Wherein d isiIs the number of neighbor agents for agent i.
Reference 1: W.Shi, Q.Ling, G.Wu, and W.yin, "A formal gradient for centralized composition optimization," IEEE Transactions on Signal Processing, vol.63, No.22, pp.6013-6023,2015.
Drawings
FIG. 1 is a graph comparing the convergence of PG-EXTRA according to the present invention;
FIG. 2 is a graph comparing the test accuracy of the present invention with PG-EXTRA;
FIG. 3 is a block diagram of four types of networks in one embodiment;
fig. 4 is a graph comparing the performance of four types of networks using the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
Example 1
A Newton momentum-based distributed acceleration composite optimization method comprises the following steps:
s1, connecting a plurality of agents into a non-directional communication network, and establishing an objective function combining a smooth structure and a non-smooth structure based on the plurality of agents:
wherein the content of the first and second substances,is a smooth local objective function known only to agent i,is a non-smooth local function known only to agent i,is the set of feasible solutions, m is the number of agents;
s2, each agent calculates its own local estimation value and sends it to the first neighbor agent, the first neighbor agent is the neighbor agent corresponding to the agent, the neighbor agents are the agents directly communicating between two agents, and each is the neighbor agent;
s3, the first neighbor agent calculates momentum acceleration item according to the received local estimation value and sends the momentum acceleration item to the second neighbor agent, and the second neighbor agent is the neighbor agent of the first neighbor agent;
s4, the second neighbor agent calculates a gradient tracking item according to the momentum acceleration item and sends the gradient tracking item to a third neighbor agent, and the third neighbor agent is an agent of the second neighbor agent;
s5, loop S2 to S4, and terminate the loop until a preset condition is met.
On the basis that a plurality of agents are connected into a non-directional network, a smooth structure and a non-smooth structure are combined to form an objective function, so that the coverage range of the processed problems is wider, the established model is more accurate, the problem can be converged to a global optimal solution at a linear speed, the convergence speed is higher than that of a similar method by introducing a momentum acceleration item and a gradient tracking item, and the processing speed of large-scale intelligent automatic equipment data can be effectively improved. The intelligent agent is a device with computing capability, storage capability and communication capability, and can be a computer, a server, an unmanned aerial vehicle, an automobile and the like. The corresponding neighbor agent should be understood as: since each agent is calculating its own local estimate in S2, each agent is transmitting the local estimate at the same time, and each agent has its own neighbor agent, i.e., the first neighbor agent. Undirected networks should be understood as: and a connection mode for enabling a plurality of agents to mutually transmit and receive information. The preset conditions include: the iteration number, the running time or the value of the target problem are within a preset interval and the like. A smooth function is a function of infinite order, continuously derivable within its domain of definition. A non-smooth function is a function that is not infinitely derivable within its domain of definition. The calculation process of the local estimation in S2 is:
s201, each agent calculates local optimal solution of each agentThe calculation formula is as follows:
s202, calculating local estimation value of the local optimal solution according to the local optimal solutionThe calculation formula is as follows:
wherein the content of the first and second substances,is thatIn the form of a continuous convex approximation of (a), is fiIn thatIs a positive constant step.
The variable updating is carried out by using a distributed optimization strategy and using continuous convex approximation replacement of the objective function instead of the objective function, so that the advantage that when the objective problem is not convex, the immobile point can still be solved for the objective problem, and when the introduced step length alpha is positive and smaller than a given upper bound, the problem which can be modeled as a convex function can be converged to the global optimal solution at a linear speed.
The calculation process of the momentum acceleration term in the S3 is as follows:
s301, carrying out weighted average on the local estimation to obtain local average estimationThe calculation formula is as follows:
s302, estimating according to local averageAnd calculating a momentum acceleration term, wherein the calculation formula is as follows:
In the steps S301 and S302, the gradient is calculated by using a Newton momentum method, and the method has the advantages that under the condition that the updating direction is the same as the previous moment, the convergence speed can be accelerated to a certain extent, the updating direction of the gradient is adjusted, the stability of the distributed optimization method is improved, and the time overhead for solving the global optimal solution is reduced. The similar method also has a common momentum method, but the common momentum method is easy to have the condition of large fluctuation of variable values in the iteration process, and the system is unstable.
In this embodiment, an undirected graph is definedWhereinIs a set of agents that are intelligent agents,is a set of edges that are to be considered,is a weighted adjacency matrix in which the weights w for the edges (i, j)ijThe following conditions are satisfied: if (i, j) ∈ then wij> 0, otherwise wij=0,Wherein d isiIs the number of neighbor agents to agent i, let self-loops exist, i.e. (i, i) ∈, and letAgents i and j can communicate directly if and only if there is an edge (i, j) e.
The specific calculation formula of the gradient tracking term in the S4 is as follows:
By carrying out gradient tracking, the local agent can also track the global gradient value, and the situation that the local optimal solution is solved because the agent can only master local information is avoided.
To verify the convergence of the present invention, the following assumptions are made:
assume that 1: (i) collectionIs a closed and convex set; (ii) local objective functionIn the first order of the gradient of (1), whereinIs an open set; gradient of gradientIn the collectionUpper LiLiphoz continuous; (iii) function(s)Is convex and may be non-smooth; (iv) function U is inThe upper boundary is lower boundary.
Assume 2: function F in setThe method is characterized in that the method mainly comprises the following steps of (1) performing optimization on a high-degree mu-strong convex, wherein the high convexity is used for optimization, and particularly one of the conditions for ensuring the linear convergence rate of a plurality of algorithms based on a gradient descent method is defined as follows:
it is noted that strong convexity does not require that the function be differentiable from place to place, and when the function is not smooth, the gradient is replaced by a sub-gradient in which strong convexity is more strictly a quadratic term than a normal convex functionThis strongly convex nature is important. Intuitive from a one-dimensional function, a convex function only requires that the function curve be above its tangent, and there is little requirement for "up", meaning that the curve can "follow" the tangent indefinitely, as long as it remains above it. It goes without saying that in optimization, in particular in gradient optimization, such weak gradient changes make it difficult to achieve fast optimization, possibly with a limited number of times that convergence has not yet been reached. This is also difficult if we take a solution close to the minimum. "very" close is only a qualitative understanding, in which case a bad situation occurs where the optimal solution is very similar but the decision variables differ greatly. At this time, a secondary term is added, so that a secondary lower bound is ensured, the condition of 'clinging' to a tangent line is avoided, and the optimization is simpler.
Assume that 3: undirected graph G is connected.
Definition 1: for a function with continuous first order gradientWhereinAnd aggregateIs a closed and convex set. If it is notIs continuous and satisfies the condition that (i) for all(ii) Gradient of gradientIs that-rishoz continuous; (iii) function(s)In the collectionIs thatAnd (4) strong convex. Then functionIs fiOf functions-the smoothness of the film is improved,successive convex approximation replacement of strong convex, whereinRefers toPartial derivatives in the parameters (x, y).
Assume 4: function(s)Is fiIs/are as followsIs smooth andstrongly convex successive convex approximation to the substitution function.
And (3) convergence analysis:
introduction 1: let 1-4 be true, for all k ≧ 0 available,
pk+1≤σ(α,β)pk+η(α,β)||k||2 (4)
wherein the parameters σ (α, β) and η (α, β) are defined as follows
and (3) proving that: according to the proposed method and pkDefinition of (1), to know
By utilizing the continuous property of the Lipruztz,
The combined formulas (8) and (9) are obtained,
Wherein the content of the first and second substances,the next step will be to determineThe lower bound of (c). Review ofCan be defined by
Using the mu-strong convex nature of the function F, it can be shown that the following holds
pk+1≤σ(α,β)pk+η(α,β)||k||2 (17)
And finishing the guiding certification.
2, leading: let 1-3 hold, for all k ≧ 0, the following holds
And (3) proving that: according to |k||2By definition in Lesion 1, it is understood that
Because of the gradient of the magnetic field, the gradient,is Li --Liphoz continuous, analytically available
And finishing the guiding certification.
And 3, introduction: let hypothesis 3 be true, for all k ≧ 0, the following holds
Thus, it is known that
Wherein the content of the first and second substances,sis greater than 0. And finishing the guiding certification.
And (4) introduction: the following equation holds under the condition that 1 to 4 hold
Wherein the content of the first and second substances,y>0。
Thus, it is possible to obtain
WhereinyIs greater than 0. And finishing the guiding certification.
And (5) introduction: let assumption 1-4 be true, then the following equation holds
Thus, the analysis can be found
Using x*Global of (2)Optimality and convexity of G (-) can be obtained
The combination of formulas (26) and (27) is known
Further, utilizeIs/are as followsStrong convexity and according toIs thatTo obtain an optimal solutionThus, the analysis can be found
And finishing the guiding certification.
And (6) introduction: according to the sequence skFor all k ≧ 0, defineAndwhereinIf it is notIs bounded, then
To analyze the linear convergence speed of the present invention using lemma 6, the following variables were defined:
the next step will be to process the sequence { p using the lemmas 1, 3-6k}, And { | | dkAnd thus demonstrates linear convergence.
The main results are:
proposition 1: let assumptions 1-4 hold. Considering sigma (alpha), eta (alpha) and two free variabless> 0 and omegay> 0, for arbitrary
The following inequality holds
Wherein the content of the first and second substances,
and (3) proving that: using theorem 1 and considering s for positive sequenceskAndis provided withCan obtain the product
A finishing formula (42) whenThen, it is found that the expression (30) holds. Similar to the analysis process for equation (30), equations (31) and (32) hold.
And finishing the guiding certification.
Theorem 1: let assumptions 1-4 hold if α and β satisfy
And 0 < beta < 1, objective functionWill be at speedLinear convergence when α ∈ [ min { α, α)max},αmax) When the temperature of the water is higher than the set temperature,and when alpha is epsilon (0, min { alpha, alpha)max}) of the two or more,
and (3) proving that: according to proposition 1, it can be known
and is
Using lemma 6, it can be seen that if some parameters exist, thenI.e. omega (alpha, beta, z) < 1, thenWill be at a linear rateConverge to 0. For this purpose, the selection of suitable parameters is minimizedAndconsider thatThere is therefore a parameter θ > 0' such that
In thatThe minimum value is obtained. In other words, it is possible to provide a high-quality image
And isBased on the previous analysis, the appropriate 3 variables ω were selectedopt,s,ySo thatBecome sufficient conditions of
Wherein the content of the first and second substances,summarize the above analysisIt can be known that
Wherein the content of the first and second substances,to ensureThe value range of (a) is not null, alpha should satisfy
Then
Therefore, if α ∈ [ min { α, α [ ], α is knownmax},αmax) Then
In this embodiment, a logistic regression simulation experiment is performed based on breast cancer data provided by the UCI machine learning database to verify the effectiveness of the method. Features of this data include Radius (Radius), Texture (Texture), circumference (Perimeter), Area (Area), and Smoothness (Smoothness) of the nucleus, etc., as calculated from digitized images of breast masses. The experiment is intended to predict whether a patient's condition is malignant based on the sample values given in the data set. The prediction probability can be expressed as
Where c and l are the data and label, respectively, for the sample. From 683 data in the data set, 200 samples of N are distributed to m networked intelligent agents for trainingThe remaining 483 samples were used for testing. The j-th data and sample of agent i are respectivelyAnd li,hE { -1, 1}, whereinh=1,...,qi。
Based on the model, classifierAbout sample data (c)i,h,li,h) The maximum log-likelihood estimate of (c) is the optimal solution to the following optimization problem:
wherein the regularization termFor the purpose of avoiding over-fitting,for increasing the sparsity of the solution. The residual error is defined as in the following simulation
In this example, the convergence of the PG-EXTRA method and the proposed method is compared in reference 1. Defining initial valuesAndsetting the step length α to 0.01, the momentum term coefficient β to 0.5, and setting the preset condition to be the number of iterations to 70, it should be understood that the number of iterations is different for different data samples, and the setting is here according to actual requirements. A undirected network of m-10 agents is randomly generated with a 70% probability of direct communication between each pair of agents. The evolution of the residual with respect to the different methods is shown in fig. 1, and the test accuracy is shown in fig. 2. As can be seen from fig. 1, when α is 0.01, the convergence rate of the proposed method is faster than that of reference 1, and the data processing speed is greatly increased.
It should be noted that the disclosure in reference 1 is mainly used for comparison with the present invention, and does not disclose the technical contents of the present invention, nor suggest the technical problems and technical solutions solved by the present invention.
In the present embodiment, a network including a star network a, a ring network b, a tree network c, and a fully connected network d as shown in fig. 3 is also studied. Setting an initial value toAndand sets the step size alpha to 0.01 and the momentum parameter beta to 0.5. The performance of the proposed method under each type of network is shown in fig. 4, and the result shows that the convergence speed is higher and the data processing speed is higher when the network is dense.
Example 2
On the basis of the embodiment 1, the Newton momentum-based distributed acceleration composite optimization system comprises an objective function establishing module and a plurality of intelligent agents which are connected into a non-directional communication network;
the target function establishing module is used for establishing a target function combining a smooth structure and a non-smooth structure according to a plurality of agents:
wherein the content of the first and second substances,is a smooth local objective function known only to agent i,is a non-smooth local function known only to agent i,is the set of feasible solutions, m is the number of agents;
the system comprises a plurality of intelligent agents, a first neighbor intelligent agent and a second neighbor intelligent agent, wherein the plurality of intelligent agents are used for calculating local estimated values of the intelligent agents and sending the local estimated values to the first neighbor intelligent agent;
the first neighbor agent is used for calculating momentum acceleration terms according to the received local estimated values and sending the momentum acceleration terms to the second neighbor agent, and the second neighbor agent is a neighbor agent of the first neighbor agent;
the second neighbor agent is used for calculating a gradient tracking item according to the momentum acceleration item and sending the gradient tracking item to a third neighbor agent, and the third neighbor agent is an agent of the second neighbor agent;
the plurality of agents are further configured to loop the local estimates, the momentum acceleration term, and the gradient tracking term until a predetermined condition is met.
In this embodiment, a single agent is a drone with traffic capacity, computing capacity and storage capacity, and a undirected network connected by a plurality of agents means that the agents can communicate with each other. The first neighbor agent, the second neighbor agent and the third neighbor agent are all contained in a plurality of agents, and the target function is solved by the cooperation of the plurality of agents; the preset conditions include: the iteration number, the running time or the value of the target problem are within a preset interval and the like.
The calculation process of the local estimation is as follows:
s201, each agent calculates local optimal solution of each agentThe calculation formula is as follows:
s202, calculating local estimation value of the local optimal solution according to the local optimal solutionThe calculation formula is as follows:
wherein the content of the first and second substances,is thatIn the form of a continuous convex approximation of (a), is fiIn thatIs a positive constant step.
On the basis that a plurality of agents are connected into a non-directional network, a smooth structure and a non-smooth structure are combined to form an objective function, so that the coverage range of the processed problems is wider, the established model is more accurate, the problem can be converged to a global optimal solution at a linear speed, the convergence speed is higher than that of a similar method by introducing a momentum acceleration item and a gradient tracking item, and the processing speed of large-scale intelligent automatic equipment data can be effectively improved.
The momentum acceleration term is calculated as follows:
s301, carrying out weighted average on the local estimation to obtain local average estimationThe calculation formula is as follows:
s302, estimating according to local averageAnd calculating a momentum acceleration term, wherein the calculation formula is as follows:
The variable updating is carried out by using a distributed optimization strategy and using continuous convex approximation replacement of the objective function instead of the objective function, so that the advantage that when the objective problem is not convex, the immobile point can still be solved for the objective problem, and when the introduced step length alpha is positive and smaller than a given upper bound, the problem which can be modeled as a convex function can be converged to the global optimal solution at a linear speed.
The specific calculation formula of the gradient tracking term is as follows:
By carrying out gradient tracking, the local agent can also track the global gradient value, and the situation that the local optimal solution is solved because the agent can only master local information is avoided.
wijThe value rule is as follows:
defining an undirected graphWhereinIs a set of agents that are intelligent agents,is a set of edges that are to be considered,is a weighted adjacency matrix in which the weights w for the edges (i, j)ijThe following conditions are satisfied: if (i, j) ∈ then wij> 0, otherwise wij=0,Wherein d isiIs the number of neighbor agents for agent i.
In this embodiment, adopt a plurality of unmanned aerial vehicles to solve the problem of target location, every unmanned aerial vehicle can all be regarded as an agent, and specific implementation process is as follows:
firstly, a sound source/energy source is planned to continuously send signals outwards, as the propagation of the volume is gradually attenuated along with the increase of the distance, a plurality of unmanned aerial vehicles establish an objective function related to the distance and the information intensity according to the received intensity, the communication and the information calculation are carried out among the unmanned aerial vehicles, and finally, the target position is obtained, and the rapid positioning is realized.
Example 3
On the basis of embodiment 1, solve the resource allocation problem with the intelligent generator of many microprocessor control, be intelligent agent at every microprocessor:
for example, assuming that there are several different power generators, the power generator generates power with coal, the relationship between the amount of coal used and the amount of power generated is positively correlated, and the utilization rate of coal is different for each power generator, some are high, and some are low. How to effectively utilize limited coal is the problem solved by the case.
Aiming at the performances of different generators, a mathematical model between the generated energy and the coal consumption is established, an objective function related to the generated energy is obtained, and a function value is the coal consumption. The microprocessors are combined with the specific conditions of the corresponding generators, communication and information calculation are carried out among the microprocessors, and finally the coal consumption of each generator is obtained.
The technical solutions provided by the embodiments of the present invention are described in detail above, and the principles and embodiments of the present invention are explained herein by using specific examples, and the descriptions of the embodiments are only used to help understanding the principles of the embodiments of the present invention; also, while the present invention has been described with respect to particular embodiments and with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that the foregoing descriptions of the present invention are provided for illustration and not for the purpose of limiting the invention as defined by the appended claims.
Claims (10)
1. A Newton momentum-based distributed acceleration composite optimization method is characterized by comprising the following steps:
s1, connecting a plurality of agents into a non-directional communication network, and establishing an objective function combining a smooth structure and a non-smooth structure based on the agents:
wherein the content of the first and second substances,is a smooth local objective function known only to agent i,is a non-smooth local function known only to agent i,is the set of feasible solutions, m is the number of agents;
s2, each agent calculates its own local estimation value and sends it to the first neighbor agent, the first neighbor agent is the neighbor agent corresponding to the agent, the neighbor agents are the agents directly communicating between two agents, and each is the neighbor agent;
s3, the first neighbor agent calculates momentum acceleration item according to the received local estimation value and sends the momentum acceleration item to a second neighbor agent, and the second neighbor agent is the neighbor agent of the first neighbor agent;
s4, the second neighbor agent calculates a gradient tracking item according to the momentum acceleration item and sends the gradient tracking item to a third neighbor agent, and the third neighbor agent is an agent of the second neighbor agent;
s5, loop S2 to S4, and terminate the loop until a preset condition is met.
2. The method of claim 1, wherein the local estimation in S2 is calculated by:
s201, each agent calculates local optimal solution of each agentThe calculation formula is as follows:
s202, calculating the local estimation value of the local optimal solution according to the local optimal solutionThe calculation formula is as follows:
3. The method according to claim 2, wherein the calculation process of the momentum acceleration term in S3 is as follows:
s301, the local estimation is carried outWeighted averaging to obtain a locally averaged estimateThe calculation formula is as follows:
s302, estimating according to the local averageCalculating the momentum acceleration term according to the following calculation formula:
5. The method of claim 4, wherein w isijThe value rule is as follows: defining an undirected graphWhereinIs a set of agents that are intelligent agents,is a set of edges that are to be considered,is a weighted adjacency matrix in which the weights w for the edges (i, j)ijThe following conditions are satisfied: if (i, j) ∈ then wij> 0, otherwise wij=0,Wherein d isiIs the number of neighbor agents for agent i.
6. A Newton momentum-based distributed acceleration composite optimization system is characterized by comprising an objective function establishing module and a plurality of intelligent agents which are connected into a non-directional communication network;
the objective function establishing module is used for establishing an objective function combining a smooth structure and a non-smooth structure according to the plurality of agents:
wherein the content of the first and second substances,is a smooth local objective function known only to agent i,is a non-smooth local function known only to agent i,is the set of feasible solutions, m is the number of agents;
the intelligent agents are used for calculating local estimation values of the intelligent agents and sending the local estimation values to a first neighbor intelligent agent, the first neighbor intelligent agent is a neighbor intelligent agent corresponding to the intelligent agent, the neighbor intelligent agents are intelligent agents which directly communicate between the two intelligent agents, and the neighbor intelligent agents are neighbor intelligent agents;
the first neighbor agent is used for calculating momentum acceleration items according to the received local estimation values and sending the momentum acceleration items to a second neighbor agent, and the second neighbor agent is a neighbor agent of the first neighbor agent;
the second neighbor agent is used for calculating a gradient tracking item according to the momentum acceleration item and sending the gradient tracking item to a third neighbor agent, and the third neighbor agent is an agent of the second neighbor agent;
the plurality of agents are further configured to loop the local estimates, the momentum acceleration term, the gradient tracking term until a predetermined condition is met and terminate the loop.
7. The system of claim 6, wherein the local estimate is calculated by:
s201, each agent calculates local optimal solution of each agentThe calculation formula is as follows:
s202, calculating the local estimation value of the local optimal solution according to the local optimal solutionThe calculation formula is as follows:
8. The system of claim 7, wherein the momentum acceleration term is calculated by:
s301, carrying out weighted average on the local estimation values to obtain local average estimation valuesThe calculation formula is as follows:
s302, estimating according to the local averageCalculating the momentum acceleration term according to the following calculation formula:
10. The system of claim 9, wherein w isijThe value rule is as follows: defining an undirected graphWhereinIs a set of agents that are intelligent agents,is a set of edges that are to be considered,is a weighted adjacency matrix in which the weights w for the edges (i, j)ijThe following conditions are satisfied: if (i, j) ∈ then wij> 0, otherwise wij=0,Wherein d isiIs the number of neighbor agents for agent i.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010709580.7A CN111950194B (en) | 2020-07-22 | 2020-07-22 | Newton momentum-based distributed acceleration composite optimization method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010709580.7A CN111950194B (en) | 2020-07-22 | 2020-07-22 | Newton momentum-based distributed acceleration composite optimization method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111950194A true CN111950194A (en) | 2020-11-17 |
CN111950194B CN111950194B (en) | 2023-04-07 |
Family
ID=73341190
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010709580.7A Active CN111950194B (en) | 2020-07-22 | 2020-07-22 | Newton momentum-based distributed acceleration composite optimization method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111950194B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102393709A (en) * | 2011-10-27 | 2012-03-28 | 上海交通大学 | Optimization method of multi-agent synchronization problem |
US20170337682A1 (en) * | 2016-05-18 | 2017-11-23 | Siemens Healthcare Gmbh | Method and System for Image Registration Using an Intelligent Artificial Agent |
US20180164835A1 (en) * | 2016-09-27 | 2018-06-14 | Arizona Board Of Regents On Behalf Of Arizona State University | Systems and methods for dynamics, modeling, simulation and control of mid-flight coupling of quadrotors |
AU2020100078A4 (en) * | 2020-01-16 | 2020-02-13 | Southwest University | A Distributed Generalization and Acceleration Strategy for Convex Optimization Problem |
CN110933056A (en) * | 2019-11-21 | 2020-03-27 | 博智安全科技股份有限公司 | Anti-attack multi-agent control system and method thereof |
CN111259327A (en) * | 2020-01-15 | 2020-06-09 | 桂林电子科技大学 | Subgraph processing-based optimization method for consistency problem of multi-agent system |
AU2020100842A4 (en) * | 2020-05-26 | 2020-07-02 | Southwest University | An efficient and accelerated distributed algorithm for smart grids |
-
2020
- 2020-07-22 CN CN202010709580.7A patent/CN111950194B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102393709A (en) * | 2011-10-27 | 2012-03-28 | 上海交通大学 | Optimization method of multi-agent synchronization problem |
US20170337682A1 (en) * | 2016-05-18 | 2017-11-23 | Siemens Healthcare Gmbh | Method and System for Image Registration Using an Intelligent Artificial Agent |
US20180164835A1 (en) * | 2016-09-27 | 2018-06-14 | Arizona Board Of Regents On Behalf Of Arizona State University | Systems and methods for dynamics, modeling, simulation and control of mid-flight coupling of quadrotors |
CN110933056A (en) * | 2019-11-21 | 2020-03-27 | 博智安全科技股份有限公司 | Anti-attack multi-agent control system and method thereof |
CN111259327A (en) * | 2020-01-15 | 2020-06-09 | 桂林电子科技大学 | Subgraph processing-based optimization method for consistency problem of multi-agent system |
AU2020100078A4 (en) * | 2020-01-16 | 2020-02-13 | Southwest University | A Distributed Generalization and Acceleration Strategy for Convex Optimization Problem |
AU2020100842A4 (en) * | 2020-05-26 | 2020-07-02 | Southwest University | An efficient and accelerated distributed algorithm for smart grids |
Non-Patent Citations (2)
Title |
---|
ZHENG WANG,LIFENG ZHENG,HUAQING LI: ""Distributed Optimization over General Directed Networks with Rando Sleep Scheme"", 《INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS》 * |
郑李逢: ""基于多智能体系统的快速分布式优化算法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN111950194B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110968426A (en) | Edge cloud collaborative k-means clustering model optimization method based on online learning | |
CN103730006A (en) | Short-time traffic flow combined forecasting method | |
CN104156984A (en) | PHD (Probability Hypothesis Density) method for multi-target tracking in uneven clutter environment | |
Han et al. | Network traffic prediction using variational mode decomposition and multi-reservoirs echo state network | |
CN113469325A (en) | Layered federated learning method, computer equipment and storage medium for edge aggregation interval adaptive control | |
CN104539601A (en) | Reliability analysis method and system for dynamic network attack process | |
CN115525038A (en) | Equipment fault diagnosis method based on federal hierarchical optimization learning | |
Jarvenpaa et al. | Batch simulations and uncertainty quantification in Gaussian process surrogate approximate Bayesian computation | |
Zhang et al. | Method of predicting bus arrival time based on MapReduce combining clustering with neural network | |
Li et al. | Model-distributed dnn training for memory-constrained edge computing devices | |
Zhang et al. | A method based on Lorenz disturbance and variational mode decomposition for wind speed prediction | |
CN113891275A (en) | Underwater wireless sensor network trust model based on transfer learning | |
CN117151208B (en) | Asynchronous federal learning parameter updating method based on self-adaptive learning rate, electronic equipment and storage medium | |
Zhao et al. | Adaptive Swarm Intelligent Offloading Based on Digital Twin-assisted Prediction in VEC | |
CN111950194B (en) | Newton momentum-based distributed acceleration composite optimization method and system | |
CN115577290A (en) | Distribution network fault classification and source positioning method based on deep learning | |
CN115834580B (en) | Ocean big data-oriented distributed data processing method, device and equipment | |
Gong et al. | A mixture model parameters estimation algorithm for inter-contact times in internet of vehicles | |
Asheralieva et al. | Ultra-Reliable Low-Latency Slicing in Space-Air-Ground Multi-Access Edge Computing Networks for Next-Generation Internet of Things and Mobile Applications | |
Kim et al. | K-FL: Kalman Filter-based Clustering Federated Learning Method | |
Zhang et al. | Performance analysis of parallel/distributed particle filters | |
CN110768841A (en) | Acceleration distributed online optimization method based on condition gradient | |
Mahmoudi et al. | A-LAQ: Adaptive Lazily Aggregated Quantized Gradient | |
CN116546429B (en) | Vehicle selection method and system in federal learning of Internet of vehicles | |
CN114580578B (en) | Method and device for training distributed random optimization model with constraints and terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |