Stochastic Markov gradient descent and training low-bit neural networks

DOI10.1007/S43670-021-00015-1OpenAlexW3206635749MaRDI QIDQ2073135FDOQ2073135

Jonathan Ashbrock, Alexander M. Powell

Publication date: 27 January 2022

Published in: Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.11117

zbMATH Keywords

neural networksquantizationstochastic gradient descentlow-memory trainingstochastic Markov gradient descent

Mathematics Subject Classification ID

Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximation by superpositions of a sigmoidal function
• Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm
• Universality of deep convolutional neural networks
• Deep distributed convolutional neural networks: Universality
• Lipschitz properties for deep convolutional networks
• Blended coarse gradient descent for full quantization of deep neural networks
• Deep Network Approximation Characterized by Number of Neurons
• Least-Squares Halftoning via Human Vision System and Markov Gradient Descent (LS-MGD): Algorithm and Analysis

Cited In (4)

• PAC-learning with approximate predictors
• Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks
• Stochastic quantization for learning accurate low-bit deep neural networks
• Approximation with one-bit polynomials in Bernstein form

Uses Software

• ImageNet
• AdaGrad
• Adam
• BinaryConnect
• BinaryNet
• DoReFa-Net
• AlexNet
• XNOR-Net

This page was built for publication: Stochastic Markov gradient descent and training low-bit neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2073135)