AU2019101446A4 - A fast distributed strategy for large-scale machine learning - Google Patents

A fast distributed strategy for large-scale machine learning Download PDF

Info

Publication number
AU2019101446A4
AU2019101446A4 AU2019101446A AU2019101446A AU2019101446A4 AU 2019101446 A4 AU2019101446 A4 AU 2019101446A4 AU 2019101446 A AU2019101446 A AU 2019101446A AU 2019101446 A AU2019101446 A AU 2019101446A AU 2019101446 A4 AU2019101446 A4 AU 2019101446A4
Authority
AU
Australia
Prior art keywords
agent
variables
algorithm
gradient
parameters
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.)
Ceased
Application number
AU2019101446A
Inventor
Jinhui Hu
Huaqing Li
Zheng Wang
Lifeng Zheng
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest University
Original Assignee
Southwest University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southwest University filed Critical Southwest University
Priority to AU2019101446A priority Critical patent/AU2019101446A4/en
Application granted granted Critical
Publication of AU2019101446A4 publication Critical patent/AU2019101446A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G06F15/161—Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G06F15/163—Interprocessor communication
    • G06F15/173—Interprocessor communication using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/70—Services for machine-to-machine communication [M2M] or machine type communication [MTC]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Multi Processors (AREA)

Abstract

Abstract A fast distributed strategy based on heavy-ball method for solving optimization problems which are defined in a time-varying directed networked multi-agent system is proposed. The algorithm mainly comprises five parts including determining parameter; variable initializa tion; exchanging information; computing gradient; updating variable. By simultaneously implementing both row- and column-stochastic matrices, the algorithm which is set forth in the present invention removes the conservatism in the related work due to doubly-stochastic matrices. Under conditions that the global objective function is strongly convex and each local objective function has Lipschitz-continuous gradient, the fast distributed algorithm can linearly converge to the global optimization solution with proper uncoordinated step sizes and momentum parameters. The present invention has broad application in large-scale machine learning. Start Each agent sets k=O and maximum number of iterations, kwax Each agent initializes local variables. Compute system parameters Select a step size according to the parameters Each agent sends variables to its neighbor agents Each agent updates the variables and computes the gradient Each agent sets k=k+1 k>kmax? End Figure 1
AU2019101446A 2019-11-23 2019-11-23 A fast distributed strategy for large-scale machine learning Ceased AU2019101446A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2019101446A AU2019101446A4 (en) 2019-11-23 2019-11-23 A fast distributed strategy for large-scale machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2019101446A AU2019101446A4 (en) 2019-11-23 2019-11-23 A fast distributed strategy for large-scale machine learning

Publications (1)

Publication Number Publication Date
AU2019101446A4 true AU2019101446A4 (en) 2020-01-23

Family

ID=69166829

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2019101446A Ceased AU2019101446A4 (en) 2019-11-23 2019-11-23 A fast distributed strategy for large-scale machine learning

Country Status (1)

Country Link
AU (1) AU2019101446A4 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112100811A (en) * 2020-08-13 2020-12-18 西北工业大学 Antenna array directional diagram synthesis method based on adaptive wind-driven optimization algorithm
CN112714165A (en) * 2020-12-22 2021-04-27 声耕智能科技(西安)研究院有限公司 Distributed network cooperation strategy optimization method and device based on combination mechanism
CN118041471A (en) * 2024-04-11 2024-05-14 成都信息工程大学 Spectrum sensing method and system based on machine learning logistic regression algorithm

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112100811A (en) * 2020-08-13 2020-12-18 西北工业大学 Antenna array directional diagram synthesis method based on adaptive wind-driven optimization algorithm
CN112714165A (en) * 2020-12-22 2021-04-27 声耕智能科技(西安)研究院有限公司 Distributed network cooperation strategy optimization method and device based on combination mechanism
CN118041471A (en) * 2024-04-11 2024-05-14 成都信息工程大学 Spectrum sensing method and system based on machine learning logistic regression algorithm
CN118041471B (en) * 2024-04-11 2024-06-11 成都信息工程大学 Spectrum sensing method and system based on machine learning logistic regression algorithm

Similar Documents

Publication Publication Date Title
AU2019101446A4 (en) A fast distributed strategy for large-scale machine learning
WO2017083399A3 (en) Training neural networks represented as computational graphs
WO2019072289A3 (en) Blockchain smart contract updates using decentralized decision
WO2019070644A3 (en) Systems and methods for utilizing multicriteria optimization in additive manufacture
WO2020012434A3 (en) Systems and methods for intraocular lens selection
GB2549208A (en) System and method for image reconstruction
WO2015101461A3 (en) Method and apparatus for design of a metrology target
EP4174590A3 (en) Combined learned and dynamic control method
JPWO2022044064A5 (en) Machine learning data generation program, machine learning data generation method and machine learning data generation device
ATE417696T1 (en) OPTIMIZATION OF SEQUENTIAL COMBINATORY PROCESSES
CN110378583B (en) Method for interchanging adjacent procedures of pseudo-critical path and equipment
CN104808629A (en) Flexible robot manufacturing unit scheduling method
CN111160755A (en) DQN-based real-time scheduling method for aircraft overhaul workshop
Hiroyasu et al. Parallel simulated annealing using genetic crossover
AU2003265712A1 (en) Method for the computer-supported generation of prognoses for operative systems and system for the generation of prognoses for operative systems
GB2554287A (en) Animating a virtual object in a virtual world
CN108107848B (en) Assembly line workshop scheduling method based on minimum idle time
CN104238624A (en) Maximum power point tracking method and device
AU2019101503A4 (en) A Distributed Stochastic Gradient Projection Strategy for Constrained Convex Optimization Problem
CN108873850A (en) A kind of Optimization Scheduling of automation of machinery manufacture production process
RU2014125265A (en) SYSTEM AND METHOD OF DYNAMIC LOCALIZATION INSTALLED IN A DEFECT PRODUCT
CN111143966A (en) Regional power grid maintenance plan generation method and system
CN106647757A (en) Robot path planning method based on combined individual difference evolution
Chunquan et al. Sitting and sizing of distribution generation by considering of reactive power optimization
Seraj et al. A fuzzy multi-objective tabu-search method for a new bi-objective open shop scheduling problem

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry