Efficient Online-Bandit Strategies for Minimax Learning Problems

05/28/2021
āˆ™
by   Christophe Roux, et al.
āˆ™
0
āˆ™

Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these problems are convex-linear problems where the minimization is carried out over the model parameters wāˆˆš’² and the maximization over the empirical distribution pāˆˆš’¦ of the training set indexes, where š’¦ is the simplex or a subset of it. To design efficient methods, we let an online learning algorithm play against a (combinatorial) bandit algorithm. We argue that the efficiency of such approaches critically depends on the structure of š’¦ and propose two properties of š’¦ that facilitate designing efficient algorithms. We focus on a specific family of sets š’®_n,k encompassing various learning applications and provide high-probability convergence guarantees to the minimax values.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
āˆ™ 05/11/2013

On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions

In this paper, we study the generalization properties of online learning...
research
āˆ™ 06/16/2020

The limits of min-max optimization algorithms: convergence to spurious non-critical sets

Compared to minimization problems, the min-max landscape in machine lear...
research
āˆ™ 10/04/2018

Non-Convex Min-Max Optimization: Provable Algorithms and Applications in Machine Learning

Min-max saddle-point problems have broad applications in many tasks in m...
research
āˆ™ 12/21/2013

Volumetric Spanners: an Efficient Exploration Basis for Learning

Numerous machine learning problems require an exploration basis - a mech...
research
āˆ™ 06/09/2023

Specifying and Solving Robust Empirical Risk Minimization Problems Using CVXPY

We consider robust empirical risk minimization (ERM), where model parame...
research
āˆ™ 02/22/2017

Fast Rates for Bandit Optimization with Upper-Confidence Frank-Wolfe

We consider the problem of bandit optimization, inspired by stochastic o...
research
āˆ™ 11/24/2021

Learning to Refit for Convex Learning Problems

Machine learning (ML) models need to be frequently retrained on changing...

Please sign up or login with your details

Forgot password? Click here to reset