Contextual Blocking Bandits

• URL: http://arxiv.org/abs/2003.03426v2
• Date: Wed, 17 Jun 2020 11:36:37 GMT
• Title: Contextual Blocking Bandits
• Authors: Soumya Basu, Orestis Papadigenopoulos, Constantine Caramanis, Sanjay Shakkottai
• Abstract summary: We study a novel variant of the multi-armed bandit problem, where at each time step, the player observes an independently sampled context that determines the arms' mean rewards. Playing an arm blocks it (across all contexts) for a fixed and known number of future time steps. We propose a UCB-based variant of the full-information algorithm that guarantees a $mathcalO(log T)$-regret w.r.t. an $alpha$regret strategy in $T time steps, matching the $Omega(log(T)$ lower bound
• Score: 35.235375147227124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study a novel variant of the multi-armed bandit problem, where at each time step, the player observes an independently sampled context that determines the arms' mean rewards. However, playing an arm blocks it (across all contexts) for a fixed and known number of future time steps. The above contextual setting, which captures important scenarios such as recommendation systems or ad placement with diverse users, invalidates greedy solution techniques that are effective for its non-contextual counterpart (Basu et al., NeurIPS19). Assuming knowledge of the context distribution and the mean reward of each arm-context pair, we cast the problem as an online bipartite matching problem, where the right-vertices (contexts) arrive stochastically and the left-vertices (arms) are blocked for a finite number of rounds each time they are matched. This problem has been recently studied in the full-information case, where competitive ratio bounds have been derived. We focus on the bandit setting, where the reward distributions are initially unknown; we propose a UCB-based variant of the full-information algorithm that guarantees a $\mathcal{O}(\log T)$-regret w.r.t. an $\alpha$-optimal strategy in $T$ time steps, matching the $\Omega(\log(T))$ regret lower bound in this setting. Due to the time correlations caused by blocking, existing techniques for upper bounding regret fail. For proving our regret bounds, we introduce the novel concepts of delayed exploitation and opportunistic subsampling and combine them with ideas from combinatorial bandits and non-stationary Markov chains coupling.

Related papers

• Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting [67.1631453378926]
  Graph-Triggered Bandits is a framework to generalize rested and restless bandits. In this work, we focus on two specific types of monotonic bandits: rising, where the expected reward of an arm grows as the number of triggers increases, and rotting, where the opposite behavior occurs.
  arXiv  Detail & Related papers  (2024-09-09T18:23:07Z)
• A General Framework for Clustering and Distribution Matching with Bandit Feedback [81.50716021326194]
  We develop a general framework for clustering and distribution matching problems with bandit feedback. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding $delta$.
  arXiv  Detail & Related papers  (2024-09-08T12:19:12Z)
• Feel-Good Thompson Sampling for Contextual Dueling Bandits [49.450050682705026]
  We propose a Thompson sampling algorithm, named FGTS.CDB, for linear contextual dueling bandits. At the core of our algorithm is a new Feel-Good exploration term specifically tailored for dueling bandits. Our algorithm achieves nearly minimax-optimal regret, i.e., $tildemathcalO(dsqrt T)$, where $d$ is the model dimension and $T$ is the time horizon.
  arXiv  Detail & Related papers  (2024-04-09T04:45:18Z)
• Optimal cross-learning for contextual bandits with unknown context distributions [28.087360479901978]
  We consider the problem of designing contextual bandit algorithms in the cross-learning'' setting of Balseiro et al. We provide an efficient algorithm with a nearly tight (up to logarithmic factors) regret bound of $widetildeO(sqrtTK)$, independent of the number of contexts. At the core of our algorithm is a novel technique for coordinating the execution of an algorithm over multiple epochs.
  arXiv  Detail & Related papers  (2024-01-03T18:02:13Z)
• Best-of-Both-Worlds Linear Contextual Bandits [45.378265414553226]
  This study investigates the problem of $K$-armed linear contextual bandits, an instance of the multi-armed bandit problem, under an adversarial corruption. We develop a strategy that is effective in both adversarial environments, with theoretical guarantees. We refer to our strategy as the Best-of-Both-Worlds (BoBW) RealFTRL, due to its theoretical guarantees in both adversarial regimes.
  arXiv  Detail & Related papers  (2023-12-27T09:32:18Z)
• 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)
• Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits [53.281230333364505]
  This paper studies the problem of contextual dueling bandits, where the binary comparison of dueling arms is generated from a generalized linear model (GLM) We propose a new SupLinUCB-type algorithm that enjoys computational efficiency and a variance-aware regret bound $tilde Obig(dsqrtsum_t=1Tsigma_t2 + dbig)$. Our regret bound naturally aligns with the intuitive expectation in scenarios where the comparison is deterministic, the algorithm only suffers from an $tilde O(d)$ regret.
  arXiv  Detail & Related papers  (2023-10-02T08:15:52Z)
• Combinatorial Blocking Bandits with Stochastic Delays [33.65025386998747]
  Recent work has considered natural variations of the multi-armed bandit problem, where the reward of each arm is a special function of the time passed since its last pulling. In this work, we extend the above model in two directions: (i) We consider the general setting where more than one arms can be played at each round, subject to feasibility constraints. We provide a tight analysis of the approximation of a natural greedy subset that always plays the maximum expected reward feasible among the available (non-blocked) arms. When the arms' expected rewards are unknown, we adapt the above algorithm into a bandit, based on
  arXiv  Detail & Related papers  (2021-05-22T02:46:04Z)
• Recurrent Submodular Welfare and Matroid Blocking Bandits [22.65352007353614]
  A recent line of research focuses on the study of the multi-armed bandits problem (MAB) We develop new algorithmic ideas that allow us to obtain a $ (1 - frac1e)$-approximation for any matroid. A key ingredient is the technique of correlated (interleaved) scheduling.
  arXiv  Detail & Related papers  (2021-01-30T21:51:47Z)
• Stochastic Bandits with Linear Constraints [69.757694218456]
  We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies. We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB)
  arXiv  Detail & Related papers  (2020-06-17T22:32:19Z)
• The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms [10.662105162882526]
  We investigate a $k$-armed bandit problem in the emphmany-armed regime. Our findings suggest a new form of emphfree exploration beneficial to greedy algorithms in the many-armed context.
  arXiv  Detail & Related papers  (2020-02-24T08:59:34Z)

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.