Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms

• URL: http://arxiv.org/abs/2309.00591v3
• Date: Wed, 29 May 2024 19:49:02 GMT
• Title: Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms
• Authors: Qining Zhang, Lei Ying,
• Abstract summary: Multi-Armed Bandit (MAB) problem with dual objectives: (i) quick identification and commitment to the optimal arm, and (ii) reward throughout a sequence of $T$ consecutive rounds. This paper introduces emphRegret Best Arm Identification (ROBAI) which aims to achieve these dual objectives.
• Score: 15.038210624870656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper considers a stochastic Multi-Armed Bandit (MAB) problem with dual objectives: (i) quick identification and commitment to the optimal arm, and (ii) reward maximization throughout a sequence of $T$ consecutive rounds. Though each objective has been individually well-studied, i.e., best arm identification for (i) and regret minimization for (ii), the simultaneous realization of both objectives remains an open problem, despite its practical importance. This paper introduces \emph{Regret Optimal Best Arm Identification} (ROBAI) which aims to achieve these dual objectives. To solve ROBAI with both pre-determined stopping time and adaptive stopping time requirements, we present an algorithm called EOCP and its variants respectively, which not only achieve asymptotic optimal regret in both Gaussian and general bandits, but also commit to the optimal arm in $\mathcal{O}(\log T)$ rounds with pre-determined stopping time and $\mathcal{O}(\log^2 T)$ rounds with adaptive stopping time. We further characterize lower bounds on the commitment time (equivalent to the sample complexity) of ROBAI, showing that EOCP and its variants are sample optimal with pre-determined stopping time, and almost sample optimal with adaptive stopping time. Numerical results confirm our theoretical analysis and reveal an interesting "over-exploration" phenomenon carried by classic UCB algorithms, such that EOCP has smaller regret even though it stops exploration much earlier than UCB, i.e., $\mathcal{O}(\log T)$ versus $\mathcal{O}(T)$, which suggests over-exploration is unnecessary and potentially harmful to system performance.

Related papers

• Cost Aware Best Arm Identification [13.380383930882784]
  We call it emphCost Aware Best Arm Identification (CABAI) We propose a simple algorithm called emphChernoff Overlap (CO), based on a square-root rule. Our results show that (i.e. ignoring the heterogeneous action cost results in sub-optimality in practice, and (ii.) simple algorithms can deliver near-optimal performance over a wide range of problems.
  arXiv  Detail & Related papers  (2024-02-26T16:27:08Z)
• Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling [73.5602474095954]
  We study the non-asymptotic performance of approximation schemes with delayed updates under Markovian sampling. Our theoretical findings shed light on the finite-time effects of delays for a broad class of algorithms.
  arXiv  Detail & Related papers  (2024-02-19T03:08:02Z)
• Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring [46.30750729936261]
  exploration by optimization (ExO) was proposed, which achieves the optimal bounds in adversarial environments. We first establish a novel framework and analysis for ExO with a hybrid regularizer. In particular, we derive a regret bound of $O(sum_a neq a* k2 log T / Delta_a)$ in which $a*$ is an optimal action, and $Delta_a$ is the suboptimality gap for action $a$.
  arXiv  Detail & Related papers  (2024-02-13T09:34:22Z)
• Combinatorial Stochastic-Greedy Bandit [79.1700188160944]
  We propose a novelgreedy bandit (SGB) algorithm for multi-armed bandit problems when no extra information other than the joint reward of the selected set of $n$ arms at each time $tin [T]$ is observed. SGB adopts an optimized-explore-then-commit approach and is specifically designed for scenarios with a large set of base arms.
  arXiv  Detail & Related papers  (2023-12-13T11:08:25Z)
• Non-stationary Online Convex Optimization with Arbitrary Delays [50.46856739179311]
  This paper investigates the delayed online convex optimization (OCO) in non-stationary environments. We first propose a simple algorithm, namely DOGD, which performs a gradient descent step for each delayed gradient according to their arrival order. We develop an improved algorithm, which reduces those dynamic regret bounds achieved by DOGD to $O(sqrtbardT(P_T+1))$.
  arXiv  Detail & Related papers  (2023-05-20T07:54:07Z)
• Finite-Time Error Bounds for Greedy-GQ [20.51105692499517]
  We show that Greedy-GQ algorithm converges fast as finite-time error. Our analysis provides for faster convergence step-sizes for choosing step-sizes.
  arXiv  Detail & Related papers  (2022-09-06T15:04:57Z)
• Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination [80.53485617514707]
  This paper proposes two algorithms, a gap-based algorithm and one based on the successive elimination, for best arm identification in sub-Gaussian bandits. Specifically, for the gap-based algorithm, the sample complexity is optimal up to constant factors, while for the successive elimination, it is optimal up to logarithmic factors.
  arXiv  Detail & Related papers  (2021-11-14T21:49:58Z)
• Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits [27.279654173896372]
  We study the problem of emphdynamic regret minimization in $K$-armed Dueling Bandits under non-stationary or time varying preferences. This is an online learning setup where the agent chooses a pair of items at each round and observes only a relative binary win-loss' feedback for this pair.
  arXiv  Detail & Related papers  (2021-11-06T16:46:55Z)
• Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits [91.8283876874947]
  We design and analyze the BoBW-lil'UCB$(gamma)$ algorithm. We show that (i) no algorithm can simultaneously perform optimally for both the RM and BAI objectives. We also show that BoBW-lil'UCB$(gamma)$ outperforms a competitor in terms of the time complexity and the regret.
  arXiv  Detail & Related papers  (2021-10-16T17:52:32Z)
• Lenient Regret for Multi-Armed Bandits [72.56064196252498]
  We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. We suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some $epsilon$.
  arXiv  Detail & Related papers  (2020-08-10T08:30:52Z)

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.