A Wasserstein Minimax Framework for Mixed Linear Regression

arXiv2106.07537MaRDI QIDQ6370264FDOQ6370264

Authors: Theo Diamandis, Yonina C. Eldar, Alireza Fallah, Farzan Farnia, Asuman Ozdaglar 

Publication date: 14 June 2021

Abstract: Multi-modal distributions are commonly used to model clustered data in statistical learning tasks. In this paper, we consider the Mixed Linear Regression (MLR) problem. We propose an optimal transport-based framework for MLR problems, Wasserstein Mixed Linear Regression (WMLR), which minimizes the Wasserstein distance between the learned and target mixture regression models. Through a model-based duality analysis, WMLR reduces the underlying MLR task to a nonconvex-concave minimax optimization problem, which can be provably solved to find a minimax stationary point by the Gradient Descent Ascent (GDA) algorithm. In the special case of mixtures of two linear regression models, we show that WMLR enjoys global convergence and generalization guarantees. We prove that WMLR's sample complexity grows linearly with the dimension of data. Finally, we discuss the application of WMLR to the federated learning task where the training samples are collected by multiple agents in a network. Unlike the Expectation Maximization algorithm, WMLR directly extends to the distributed, federated learning setting. We support our theoretical results through several numerical experiments, which highlight our framework's ability to handle the federated learning setting with mixture models.

Has companion code repository: https://github.com/tjdiamandis/WMLR

This page was built for publication: A Wasserstein Minimax Framework for Mixed Linear Regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6370264)