Adaptation and learning over networks under subspace constraints – Part II: Performance Analysis

06/01/2019
by   Roula Nassif, et al.
0

Part I of this paper considered optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie in low-dimensional subspaces. Starting from the centralized projected gradient descent, an iterative and distributed solution was proposed that responds to streaming data and employs stochastic approximations in place of actual gradient vectors, which are generally unavailable. We examined the second-order stability of the learning algorithm and we showed that, for small step-sizes μ, the proposed strategy leads to small estimation errors on the order of μ. This Part II examines steady-state performance. The results reveal explicitly the influence of the gradient noise, data characteristics, and subspace constraints, on the network performance. The results also show that in the small step-size regime, the iterates generated by the distributed algorithm achieve the centralized steady-state performance.

READ FULL TEXT
research
05/21/2019

Adaptation and learning over networks under subspace constraints -- Part I: Stability Analysis

This paper considers optimization problems over networks where agents ha...
research
05/21/2019

Adaptation and learning over networks under subspace constraints

This paper considers optimization problems over networks where agents ha...
research
05/22/2018

Learning over Multitask Graphs - Part II: Performance Analysis

Part I of this paper formulated a multitask optimization problem where a...
research
05/22/2018

Learning over Multitask Graphs - Part I: Stability Analysis

This paper formulates a multitask optimization problem where agents in t...
research
12/30/2011

An Amendment of Fast Subspace Tracking Methods

Tuning stepsize between convergence rate and steady state error level or...
research
09/16/2022

Quantization for decentralized learning under subspace constraints

In this paper, we consider decentralized optimization problems where age...
research
03/04/2020

Adaptation in Online Social Learning

This work studies social learning under non-stationary conditions. Altho...

Please sign up or login with your details

Forgot password? Click here to reset