A Continuous-Time Analysis of Distributed Stochastic Gradient

DOI10.1162/neco_a_01248OpenAlexW2988239210WikidataQ91189945 ScholiaQ91189945MaRDI QIDQ5131162

Nicholas M. Boffi, Jean-Jacques E. Slotine

Publication date: 2 November 2020

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1812.10995

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Biological rhythms and synchronization (92B25)

Related Items (3)

Stochastic programming with primal-dual dynamics: a mean-field game approach ⋮ A probability approximation framework: Markov process approach ⋮ Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction

Uses Software

• Jellyfish
• AdaGrad
• HOGWILD
• Saga

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• Minimizing finite sums with the stochastic average gradient
• Stochastic methods. A handbook for the natural and social sciences
• On contraction analysis for non-linear systems
• Analytical and simulation results for stochastic Fitzhugh-Nagumo neurons and neural networks
• Introductory lectures on convex optimization. A basic course.
• On the diffusion approximation of nonconvex stochastic gradient descent
• Semigroups of stochastic gradient descent and online principal component analysis: properties and diffusion approximations
• Deep relaxation: partial differential equations for optimizing deep neural networks
• Parallel stochastic gradient algorithms for large-scale matrix completion
• On partial contraction analysis for coupled nonlinear oscillators
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Acceleration of Stochastic Approximation by Averaging
• Modular stability tools for distributed computation and control
• A variational perspective on accelerated methods in optimization
• A Contraction Theory Approach to Stochastic Incremental Stability

This page was built for publication: A Continuous-Time Analysis of Distributed Stochastic Gradient