Distributed Learning in Non-Convex Environments-Part I: Agreement at a Linear Rate

Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments. Most available works on distributed non-convex optimization pr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on signal processing Vol. 69; pp. 1242 - 1256
Main Authors: Vlaski, Stefan, Sayed, Ali H.
Format: Journal Article
Language:English
Published: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
adaptation
Aggregates
Algorithms
Annealing
Centroids
Computational geometry
Convexity
Cost function
Descent
diffusion learning
distributed optimization
Eigenvalues and eigenfunctions
gradient noise
Heuristic algorithms
Machine learning
non-convex cost
Optimization
Polynomials
Saddle points
Signal processing
Signal processing algorithms
stationary points
Stochastic optimization
Stochastic processes
ISSN:1053-587X, 1941-0476
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments. Most available works on distributed non-convex optimization problems focus on the deterministic setting where exact gradients are available at each agent. In this work and its Part II, we consider stochastic cost functions, where exact gradients are replaced by stochastic approximations and the resulting gradient noise persistently seeps into the dynamics of the algorithm. We establish that the diffusion learning strategy continues to yield meaningful estimates non-convex scenarios in the sense that the iterates by the individual agents will cluster in a small region around the network centroid. We use this insight to motivate a short-term model for network evolution over a finite-horizon. In Part II of this work, we leverage this model to establish descent of the diffusion strategy through saddle points in O(1/μ) steps, where μ denotes the step-size, and the return of approximately second-order stationary points in a polynomial number of iterations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1053-587X
1941-0476
DOI:10.1109/TSP.2021.3050858