Regularized Diffusion Adaptation via Conjugate Smoothing

09/20/2019
by   Stefan Vlaski, et al.
5

The purpose of this work is to develop and study a distributed strategy for Pareto optimization of an aggregate cost consisting of regularized risks. Each risk is modeled as the expectation of some loss function with unknown probability distribution while the regularizers are assumed deterministic, but are not required to be differentiable or even continuous. The individual, regularized, cost functions are distributed across a strongly-connected network of agents and the Pareto optimal solution is sought by appealing to a multi-agent diffusion strategy. To this end, the regularizers are smoothed by means of infimal convolution and it is shown that the Pareto solution of the approximate, smooth problem can be made arbitrarily close to the solution of the original, non-smooth problem. Performance bounds are established under conditions that are weaker than assumed before in the literature, and hence applicable to a broader class of adaptation and learning problems.

READ FULL TEXT
research
05/25/2018

Distributed Stochastic Gradient Tracking Methods

In this paper, we study the problem of distributed multi-agent optimizat...
research
03/21/2018

A Distributed Stochastic Gradient Tracking Method

In this paper, we study the problem of distributed multi-agent optimizat...
research
11/06/2021

Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization

The non-smooth finite-sum minimization is a fundamental problem in machi...
research
04/20/2021

Hypervolume-Optimal μ-Distributions on Line/Plane-based Pareto Fronts in Three Dimensions

Hypervolume is widely used in the evolutionary multi-objective optimizat...
research
04/20/2017

Performance Limits of Stochastic Sub-Gradient Learning, Part II: Multi-Agent Case

The analysis in Part I revealed interesting properties for subgradient l...
research
09/07/2009

Lower Bounds for BMRM and Faster Rates for Training SVMs

Regularized risk minimization with the binary hinge loss and its variant...

Please sign up or login with your details

Forgot password? Click here to reset