paper-with-me

Papers

Banker Online Mirror Descent

2021-06-16 · Jiatai Huang, Longbo Huang

We propose Banker-OMD, a novel framework generalizing the classical Online Mirror Descent (OMD) technique in online learning algorithm design. Banker-OMD allows algorithms to robustly handle delayed feedback, and offers a general methodology for achieving $\tilde{O}(\sqrt{T} + \sqrt{D})$-style regret bounds in various delayed-feedback online learning tasks, where $T$ is the time horizon length and $D$ is the total feedback delay. We demonstrate the power of Banker-OMD with applications to three important bandit scenarios with delayed feedback, including delayed adversarial Multi-armed bandits (MAB), delayed adversarial linear bandits, and a novel delayed best-of-both-worlds MAB setting. Banker-OMD achieves nearly-optimal performance in all the three settings. In particular, it leads to the first delayed adversarial linear bandit algorithm achieving $\tilde{O}(\text{poly}(n)(\sqrt{T} + \sqrt{D}))$ regret.

📄 PDF Abstract BibTeX arXiv:2106.08943

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning

2023-01-25 · Jiatai Huang, Yan Dai, Longbo Huang

We propose Banker Online Mirror Descent (Banker-OMD), a novel framework generalizing the classical Online Mirror Descent (OMD) technique in the online learning literature. The Banker-OMD framework almost completely decou…

Multi-Armed Bandits

Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays

2026-05-22 · Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis arxiv

We study adversarial multi-armed bandits with and without delayed feedback under a safety-aware goal: achieving minimax-optimal worst-case regret while keeping nearly constant regret relative to a designated "safe" basel…

Multi-Armed Bandits

On the Universality of Online Mirror Descent

2011-12-01 · NeurIPS 2011 12 · Nati Srebro, Karthik Sridharan, Ambuj Tewari

We show that for a general class of convex online learning problems, Mirror Descent can always achieve a (nearly) optimal regret guarantee.

Non-convex online learning via algorithmic equivalence

2022-05-30 · Udaya Ghai, Zhou Lu, Elad Hazan

We study an algorithmic equivalence technique between non-convex gradient descent and convex mirror descent. We start by looking at a harder problem of regret minimization in online non-convex optimization. We show that …

A Generalized Online Mirror Descent with Applications to Classification and Regression

2013-04-10 · Francesco Orabona, Koby Crammer, Nicolò Cesa-Bianchi

Online learning algorithms are fast, memory-efficient, easy to implement, and applicable to many prediction problems, including classification, regression, and ranking. Several online algorithms were proposed in the past…

General Classificationregression