Best Arm Identification for Stochastic Rising Bandits

• URL: http://arxiv.org/abs/2302.07510v3
• Date: Mon, 27 May 2024 18:35:39 GMT
• Title: Best Arm Identification for Stochastic Rising Bandits
• Authors: Marco Mussi, Alessandro Montenegro, Francesco Trovó, Marcello Restelli, Alberto Maria Metelli,
• Abstract summary: Rising Bandits (SRBs) model sequential decision-making problems in which the expected reward of the available options increases every time they are selected. This paper focuses on the fixed-budget Best Arm Identification (BAI) problem for SRBs. We propose two algorithms to tackle the above-mentioned setting, namely R-UCBE and R-SR.
• Score: 84.55453174601826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stochastic Rising Bandits (SRBs) model sequential decision-making problems in which the expected reward of the available options increases every time they are selected. This setting captures a wide range of scenarios in which the available options are learning entities whose performance improves (in expectation) over time (e.g., online best model selection). While previous works addressed the regret minimization problem, this paper focuses on the fixed-budget Best Arm Identification (BAI) problem for SRBs. In this scenario, given a fixed budget of rounds, we are asked to provide a recommendation about the best option at the end of the identification process. We propose two algorithms to tackle the above-mentioned setting, namely R-UCBE, which resorts to a UCB-like approach, and R-SR, which employs a successive reject procedure. Then, we prove that, with a sufficiently large budget, they provide guarantees on the probability of properly identifying the optimal option at the end of the learning process and on the simple regret. Furthermore, we derive a lower bound on the error probability, matched by our R-SR (up to constants), and illustrate how the need for a sufficiently large budget is unavoidable in the SRB setting. Finally, we numerically validate the proposed algorithms in both synthetic and realistic environments.

Related papers

• Contextual Bandits with Arm Request Costs and Delays [19.263086804406786]
  We introduce a novel extension of the contextual bandit problem, where new sets of arms can be requested with time delays and associated costs. In this setting, the learner can select multiple arms from a decision set, with each selection taking one unit of time. We design algorithms that can effectively select arms and determine the appropriate time to request new arms, thereby minimizing their regret.
  arXiv  Detail & Related papers  (2024-10-17T00:44:50Z)
• Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits [0.0]
  We propose a new distribution-free, data-driven UCB algorithm for symmetric reward distributions. We prove a near-optimal regret bound for the proposed anytime, parameter-free RMM-UCB method, even for heavy-tailed distributions.
  arXiv  Detail & Related papers  (2024-06-09T10:06:50Z)
• Optimizing Sharpe Ratio: Risk-Adjusted Decision-Making in Multi-Armed Bandits [3.5502600490147196]
  We consider the Sharpe Ratio (SR) as a critical parameter in characterizing financial time series. We propose a novel algorithm for optimizing the SR called UCB- RSSR for Regret Minimization (RM) and Best Arm Identification (BAI) We demonstrate that UCB- RSSR outperforms the only other known SR optimizing bandit algorithm, U-UCB Cassel et al (2023)
  arXiv  Detail & Related papers  (2024-05-28T14:24:36Z)
• Best Arm Identification with Fixed Budget: A Large Deviation Perspective [54.305323903582845]
  We present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms. In particular, we present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms.
  arXiv  Detail & Related papers  (2023-12-19T13:17:43Z)
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
  The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
  arXiv  Detail & Related papers  (2023-07-01T18:35:21Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)
• Stochastic Rising Bandits [40.32303434592863]
  We study a particular case of the rested and restless bandits in which the arms' expected payoff is monotonically non-decreasing. This characteristic allows designing specifically crafted algorithms that exploit the regularity of the payoffs to provide tight regret bounds. We empirically compare our algorithms with state-of-the-art methods for non-stationary MABs over several synthetically generated tasks and an online model selection problem for a real-world dataset.
  arXiv  Detail & Related papers  (2022-12-07T17:30:45Z)
• A Unifying Framework for Online Optimization with Long-Term Constraints [62.35194099438855]
  We study online learning problems in which a decision maker has to take a sequence of decisions subject to $m$ long-term constraints. The goal is to maximize their total reward, while at the same time achieving small cumulative violation across the $T$ rounds. We present the first best-of-both-world type algorithm for this general class problems, with no-regret guarantees both in the case in which rewards and constraints are selected according to an unknown model, and in the case in which they are selected at each round by an adversary.
  arXiv  Detail & Related papers  (2022-09-15T16:59:19Z)
• Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
  We argue for the use of neural generative models to characterize the worst-case distribution. This approach poses a number of implementation and optimization challenges. We find that the proposed approach yields models that are more robust than comparable baselines.
  arXiv  Detail & Related papers  (2021-03-18T14:26:26Z)
• Reward Biased Maximum Likelihood Estimation for Reinforcement Learning [13.820705458648233]
  Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed. We show that it has a regret of $mathcalO( log T)$ over a time horizon of $T$ steps, similar to state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2020-11-16T06:09:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.