Batched Kernelized Bandits: Refinements and Extensions

• URL: http://arxiv.org/abs/2603.12627v1
• Date: Fri, 13 Mar 2026 03:59:00 GMT
• Title: Batched Kernelized Bandits: Refinements and Extensions
• Abstract summary: We consider the problem of black-box optimization with noisy feedback revealed in batches.<n>For algorithmic upper bounds, (Li and Scarlett, 2022) shows that $B=O(loglog T)$ batches suffice to attain near-optimal regret.<n>We present the robust-BPE algorithm, and show that a suitably-defined cumulative regret notion incurs the same bound as the non-robust setting.
• Score: 35.245032604238276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we consider the problem of black-box optimization with noisy feedback revealed in batches, where the unknown function to optimize has a bounded norm in some Reproducing Kernel Hilbert Space (RKHS). We refer to this as the Batched Kernelized Bandits problem, and refine and extend existing results on regret bounds. For algorithmic upper bounds, (Li and Scarlett, 2022) shows that $B=O(\log\log T)$ batches suffice to attain near-optimal regret, where $T$ is the time horizon and $B$ is the number of batches. We further refine this by (i) finding the optimal number of batches including constant factors (to within $1+o(1)$), and (ii) removing a factor of $B$ in the regret bound. For algorithm-independent lower bounds, noticing that existing results only apply when the batch sizes are fixed in advance, we present novel lower bounds when the batch sizes are chosen adaptively, and show that adaptive batches have essentially same minimax regret scaling as fixed batches. Furthermore, we consider a robust setting where the goal is to choose points for which the function value remains high even after an adversarial perturbation. We present the robust-BPE algorithm, and show that a suitably-defined cumulative regret notion incurs the same bound as the non-robust setting, and derive a simple regret bound significantly below that of previous work.

Related papers

• Constrained Online Learning with Noisy Constraint Values [55.29259818039367]
  Under common feasibility, our LEDGER algorithm attains $O(sqrt T)$ expected regret and $O(sqrtTlog(eT))$ expected budget violation.<n>Neither a Slater condition, independence between feedback channels, nor an absolute constraint-value bound is needed.
  arXiv  Detail & Related papers  (2026-09-07T01:38:41Z)
• Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback [39.83169162678798]
  We study the multi-armed bandit problem with adversarially chosen delays in the Best-Both-Worlds (BoBW) framework.<n>Our main contribution is a new algorithm that matches the known lower bounds in each setting individually.<n>We provide a regret bound which scale as $sum_i>0left(log T/Delta_iright) + frac1Ksum Delta_i sigma_max$, where $Delta_i$ is the sub-optimality gap of arm $i$ and $
  arXiv  Detail & Related papers  (2025-05-30T04:05:52Z)
• Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds [1.03590082373586]
  We propose and analyze TRAiL, a regret-optimal forced exploration algorithm for linear bandits. TraiL ensures a $Omega(sqrtT)$ growth in the inference quality, measured via the minimum eigenvalue of the design (regressor) matrix. We characterize an $Omega(sqrtT)$ minimax lower bound for any algorithm on the expected regret.
  arXiv  Detail & Related papers  (2024-11-19T01:08:13Z)
• Improved Regret for Bandit Convex Optimization with Delayed Feedback [50.46856739179311]
  bandit convex optimization (BCO) with delayed feedback, where only the loss value of the action is revealed under a delay. We develop a novel algorithm, and prove that it enjoys a regret bound of $O(sqrtnT3/4+sqrtdT)$ in general. We show that the proposed algorithm can improve the regret bound to $O((nT)2/3log/3T+dlog T)$ for strongly convex functions.
  arXiv  Detail & Related papers  (2024-02-14T13:08:26Z)
• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path [80.60592344361073]
  We study the Shortest Path (SSP) problem with a linear mixture transition kernel. An agent repeatedly interacts with a environment and seeks to reach certain goal state while minimizing the cumulative cost. Existing works often assume a strictly positive lower bound of the iteration cost function or an upper bound of the expected length for the optimal policy.
  arXiv  Detail & Related papers  (2024-02-14T07:52:00Z)
• Misspecified Gaussian Process Bandit Optimization [59.30399661155574]
  Kernelized bandit algorithms have shown strong empirical and theoretical performance for this problem. We introduce a emphmisspecified kernelized bandit setting where the unknown function can be $epsilon$--uniformly approximated by a function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS) We show that our algorithm achieves optimal dependence on $epsilon$ with no prior knowledge of misspecification.
  arXiv  Detail & Related papers  (2021-11-09T09:00:02Z)
• Gaussian Process Bandit Optimization with Few Batches [49.896920704012395]
  We introduce a batch algorithm inspired by finite-arm bandit algorithms. We show that it achieves the cumulative regret upper bound $Oast(sqrtTgamma_T)$ using $O(loglog T)$ batches within time horizon $T$. In addition, we propose a modified version of our algorithm, and characterize how the regret is impacted by the number of batches.
  arXiv  Detail & Related papers  (2021-10-15T00:54:04Z)
• Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions [53.77572276969548]
  We show that the C$2$UCB algorithm has the optimal regret bound $tildeO(dsqrtkT + dk)$ for the partition matroid constraints. For general constraints, we propose an algorithm that modifies the reward estimates of arms in the C$2$UCB algorithm.
  arXiv  Detail & Related papers  (2021-01-20T04:29:18Z)
• 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)
• 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)
• Regret and Belief Complexity Trade-off in Gaussian Process Bandits via Information Thresholding [42.669970064867556]
  We show how to characterize the trade-off between regret bounds of GP bandit algorithms and complexity of the posterior distributions. We observe state of the art accuracy and complexity trade-offs for GP bandit algorithms applied to global optimization.
  arXiv  Detail & Related papers  (2020-03-23T21:05:15Z)

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.