DeepAI AI Chat
Log In Sign Up

Solving optimization problems with Blackwell approachability

by   Julien Grand-Clément, et al.

We introduce the Conic Blackwell Algorithm^+ (CBA^+) regret minimizer, a new parameter- and scale-free regret minimizer for general convex sets. CBA^+ is based on Blackwell approachability and attains O(√(T)) regret. We show how to efficiently instantiate CBA^+ for many decision sets of interest, including the simplex, ℓ_p norm balls, and ellipsoidal confidence regions in the simplex. Based on CBA^+, we introduce SP-CBA^+, a new parameter-free algorithm for solving convex-concave saddle-point problems, which achieves a O(1/√(T)) ergodic rate of convergence. In our simulations, we demonstrate the wide applicability of SP-CBA^+ on several standard saddle-point problems, including matrix games, extensive-form games, distributionally robust logistic regression, and Markov decision processes. In each setting, SP-CBA^+ achieves state-of-the-art numerical performance, and outperforms classical methods, without the need for any choice of step sizes or other algorithmic parameters.


page 1

page 2

page 3

page 4


Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving

We develop new parameter and scale-free algorithms for solving convex-co...

Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games

Regret minimization is a powerful tool for solving large-scale extensive...

Logarithmic Regret for parameter-free Online Logistic Regression

We consider online optimization procedures in the context of logistic re...

Regret Circuits: Composability of Regret Minimizers

Regret minimization is a powerful tool for solving large-scale problems;...

Faster Rates for Convex-Concave Games

We consider the use of no-regret algorithms to compute equilibria for pa...

Extragradient and Extrapolation Methods with Generalized Bregman Distances for Saddle Point Problems

In this work, we introduce two algorithmic frameworks, named Bregman ext...

Optimal No-Regret Learning in General Games: Bounded Regret with Unbounded Step-Sizes via Clairvoyant MWU

In this paper we solve the problem of no-regret learning in general game...