Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiao, Yang, Yang, Kai, Song, Dongjin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909711568207872
author Jiao, Yang
Yang, Kai
Song, Dongjin
author_facet Jiao, Yang
Yang, Kai
Song, Dongjin
contents Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network behavior analysis, risk management, etc. However, existing DRO techniques face three key challenges: 1) how to deal with the asynchronous updating in a distributed environment; 2) how to leverage the prior distribution effectively; 3) how to properly adjust the degree of robustness according to different scenarios. To this end, we propose an asynchronous distributed algorithm, named Asynchronous Single-looP alternatIve gRadient projEction (ASPIRE) algorithm with the itErative Active SEt method (EASE) to tackle the federated distributionally robust optimization (FDRO) problem. Furthermore, a new uncertainty set, i.e., constrained D-norm uncertainty set, is developed to effectively leverage the prior distribution and flexibly control the degree of robustness. Finally, our theoretical analysis elucidates that the proposed algorithm is guaranteed to converge and the iteration complexity is also analyzed. Extensive empirical studies on real-world datasets demonstrate that the proposed method can not only achieve fast convergence, and remain robust against data heterogeneity as well as malicious attacks, but also tradeoff robustness with performance.
format Preprint
id arxiv_https___arxiv_org_abs_2307_14364
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis
Jiao, Yang
Yang, Kai
Song, Dongjin
Optimization and Control
Artificial Intelligence
Machine Learning
Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network behavior analysis, risk management, etc. However, existing DRO techniques face three key challenges: 1) how to deal with the asynchronous updating in a distributed environment; 2) how to leverage the prior distribution effectively; 3) how to properly adjust the degree of robustness according to different scenarios. To this end, we propose an asynchronous distributed algorithm, named Asynchronous Single-looP alternatIve gRadient projEction (ASPIRE) algorithm with the itErative Active SEt method (EASE) to tackle the federated distributionally robust optimization (FDRO) problem. Furthermore, a new uncertainty set, i.e., constrained D-norm uncertainty set, is developed to effectively leverage the prior distribution and flexibly control the degree of robustness. Finally, our theoretical analysis elucidates that the proposed algorithm is guaranteed to converge and the iteration complexity is also analyzed. Extensive empirical studies on real-world datasets demonstrate that the proposed method can not only achieve fast convergence, and remain robust against data heterogeneity as well as malicious attacks, but also tradeoff robustness with performance.
title Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis
topic Optimization and Control
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2307.14364