paper-with-me

Papers

Solving optimization problems with Blackwell approachability

2022-02-24 · Julien Grand-Clément, Christian Kroer

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 $O(\sqrt{T})$ regret. We show how to efficiently instantiate CBA$^+$ for many decision sets of interest, including the simplex, $\ell_{p}$ 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 $O(1/\sqrt{T})$ 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.

📄 PDF Abstract BibTeX arXiv:2202.12277

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent

2020-07-28 · Gabriele Farina, Christian Kroer, Tuomas Sandholm

Blackwell approachability is a framework for reasoning about repeated games with vector-valued payoffs. We introduce predictive Blackwell approachability, where an estimate of the next payoff vector is given, and the dec…

counterfactual

Time-Dependent Blackwell Approachability and Application to Absorbing Games

2023-03-09 · Joon Kwon, Yijun Wan, Bruno Ziliotto

Blackwell's approachability (Blackwell, 1954, 1956) is a very general online learning framework where a Decision Maker obtains vector-valued outcomes, and aims at the convergence of the average outcome to a given ``targe…

Approachability in Stackelberg Stochastic Games with Vector Costs

2014-11-03 · Dileep Kalathil, Vivek Borkar, Rahul Jain

The notion of approachability was introduced by Blackwell [1] in the context of vector-valued repeated games. The famous Blackwell's approachability theorem prescribes a strategy for approachability, i.e., for `steering'…

Decision MakingReinforcement Learning

Pseudonorm Approachability and Applications to Regret Minimization

2023-02-03 · Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider 외

Blackwell's celebrated approachability theory provides a general framework for a variety of learning problems, including regret minimization. However, Blackwell's proof and implicit algorithm measure approachability usin…

Blackwell Approachability and Gradient Equilibrium are Equivalent

2026-06-25 · Brian W. Lee, Nika Haghtalab, Michael I. Jordan, Ryan J. Tibshirani arxiv

Gradient equilibrium (GEQ) is a recently introduced online optimization framework that generalizes first-order stationarity from offline optimization and abstracts problems like online conformal prediction. While GEQ has…