paper-with-me

홈 › Papers

No Regret Bound for Extreme Bandits

2015-08-12 · Robert Nishihara, David Lopez-Paz, Léon Bottou

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific task of choosing among distributions to use for random hyperparameter optimization. This work is naturally framed in the extreme bandit setting, which deals with sequentially choosing which distribution from a collection to sample in order to minimize (maximize) the single best cost (reward). Whereas the distributions in the standard bandit setting are primarily characterized by their means, a number of subtleties arise when we care about the minimal cost as opposed to the average cost. For example, there may not be a well-defined "best" distribution as there is in the standard bandit setting. The best distribution depends on the rewards that have been obtained and on the remaining time horizon. Whereas in the standard bandit setting, it is sensible to compare policies with an oracle which plays the single best arm, in the extreme bandit setting, there are multiple sensible oracle models. We define a sensible notion of "extreme regret" in the extreme bandit setting, which parallels the concept of regret in the standard bandit setting. We then prove that no policy can asymptotically achieve no extreme regret.

📄 PDF Abstract BibTeX arXiv:1508.02933

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter Optimization

Similar Papers 제목 키워드 기반

Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

2019-09-05 · Yichun Hu, Nathan Kallus, Xiaojie Mao

We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\"older class with smoothness parameter $\beta$. We show how this interpolates between two extremes that were previously…

Multi-Armed Bandits

PAC-Bayesian Analysis of Contextual Bandits

2011-12-01 · NeurIPS 2011 12 · Yevgeny Seldin, Peter Auer, John S. Shawe-Taylor, Ronald Ortner 외

We derive an instantaneous (per-round) data-dependent regret bound for stochastic multiarmed bandits with side information (also known as contextual bandits). The scaling of our regret bound with the number of states (co…

Multi-Armed Bandits

Adversarial Dueling Bandits

2020-10-27 · Aadirupa Saha, Tomer Koren, Yishay Mansour

We introduce the problem of regret minimization in Adversarial Dueling Bandits. As in classic Dueling Bandits, the learner has to repeatedly choose a pair of items and observe only a relative binary `win-loss' feedback f…

Lenient Regret and Good-Action Identification in Gaussian Process Bandits

2021-02-11 · Xu Cai, Selwyn Gomes, Jonathan Scarlett

In this paper, we study the problem of Gaussian process (GP) bandits under relaxed optimization criteria stating that any function value above a certain threshold is "good enough". On the theoretical side, we study vario…

Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need

2025-10-24 · Dhruv Sarkar, Nishant Pandey, Sayak Ray Chowdhury arxiv

Regret in stochastic multi-armed bandits traditionally measures the difference between the highest reward and either the arithmetic mean of accumulated rewards or the final reward. These conventional metrics often fail t…

Multi-Armed Bandits