A Continuous-Time Analysis of Distributed Stochastic Gradient
© 2019 Massachusetts Institute of Technology. We analyze the effect of synchronization on distributed stochastic gradient algorithms. By exploiting an analogy with dynamical models of biological quorum sensing, where synchronization between agents is induced through communication with a common signa...
Main Authors: | Boffi, Nicholas M, Slotine, Jean-Jacques E |
---|---|
Format: | Article |
Language: | English |
Published: |
MIT Press - Journals
2021
|
Online Access: | https://hdl.handle.net/1721.1/136586 |
Similar Items
-
A Continuous-Time Analysis of Distributed Stochastic Gradient
by: Boffi, Nicholas M, et al.
Published: (2022) -
Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction
by: Boffi, Nicholas M, et al.
Published: (2022) -
Nonparametric Adaptive Control and Prediction: Theory and Randomized Algorithms
by: Boffi, Nicholas M., et al.
Published: (2024) -
Beyond convexity—Contraction and global convergence of gradient descent
by: Wensing, Patrick M, et al.
Published: (2022) -
Diffusion Maps Kalman Filter for a Class of Systems with Gradient Flows
by: Shnitzer, Tal, et al.
Published: (2021)