The Sample Complexity of Multiclass and Sparse Contextual Bandits

• URL: http://arxiv.org/abs/2605.29645v1
• Date: Thu, 28 May 2026 09:12:20 GMT
• Title: The Sample Complexity of Multiclass and Sparse Contextual Bandits
• Abstract summary: We aim to identify an approximately optimal policy from a given class based on bandit feedback.<n>Motivated by bandit multiclass classification with zero-one rewards, we focus on the emph$s$-sparse setting.<n>We show that, with $s$-sparse rewards, the induced model class admits a sharp DEC bound that scales with $s$ and directly yields the optimal rate.
• Score: 106.74652380822778
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study contextual bandits in the stochastic i.i.d.\ setting, where a learner observes contexts drawn from an unknown distribution, selects actions from a finite set $A$, and aims to identify an approximately optimal policy from a given class based on bandit feedback. Motivated by bandit multiclass classification with zero-one rewards, we focus on the \emph{$s$-sparse} setting in which, for every context, the reward vector has $L_1$-norm at most $s \ll |A|$. Our main result is the design of algorithms that, with high probability, output an $ε$-optimal policy compared to policy class $Π$ using $\tilde{O} ((s/ε^2 + |A|/ε)\log |Π|/δ)$ samples. We extend this bound to general Natarajan classes and complement it with a matching lower bound (up to logarithmic factors), thereby closing a substantial gap left by prior work (Erez et al., 2024, 2025), which incurred an additional $Θ(|A|^9)$ dependence. We obtain these results via two complementary approaches. First, we analyze contextual bandits through the lens of contextual decision making with structured observations, designing an exploration-by-optimization algorithm whose sample complexity is governed by the \emph{decision-estimation coefficient} (DEC; Foster et al., 2021, 2022). We show that, with $s$-sparse rewards, the induced model class admits a sharp DEC bound that scales with $s$ and directly yields the optimal rate. Since this approach is largely information-theoretic and involves solving complex min-max optimization problems, we also develop a second, more specialized algorithmic method based on a low-variance exploration technique. This approach leads to concrete, tractable algorithms and naturally extends to contextual combinatorial semi-bandits, leading to improved sample complexity guarantees for bandit multiclass list classification.

Related papers

• Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback [0.8287206589886881]
  We study the Logistic Contextual Slate Bandit problem.<n>A single binary reward, determined by a logistic model, is observed for the chosen slate.<n>We propose two algorithms, Slate-GLM-OFU and Slate-GLM-TS, that accomplish this goal.
  arXiv  Detail & Related papers  (2025-06-16T07:19:02Z)
• From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards [26.147671458980117]
  We study the problem of contextual semi-bandits, where input contexts are mapped into subsets of size $m$ of a collection of $K$ possible actions.<n>Motivated by prototypical applications of contextual bandits, we focus on the $s$-sparse regime.<n>Our framework generalizes the list multiclass classification problem with bandit feedback, which can be seen as a special case with binary reward vectors.
  arXiv  Detail & Related papers  (2025-02-13T12:13:25Z)
• Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits [49.96531901205305]
  We analyze $f$-divergence-regularized offline policy learning.<n>For reverse Kullback-Leibler (KL) divergence, we give the first $tildeO(epsilon-1)$ sample complexity under single-policy concentrability.<n>We extend our analysis to dueling bandits, and we believe these results take a significant step toward a comprehensive understanding of $f$-divergence-regularized policy learning.
  arXiv  Detail & Related papers  (2025-02-09T22:14:45Z)
• Optimal Best Arm Identification with Post-Action Context [15.613350380708798]
  We introduce the problem of best arm identification with post-action context.<n>We analyze two different types of the post-action context.<n>For the non-separator setting, we do so by demonstrating that the Track-and-Stop algorithm can be extended to this setting.<n>For the separator setting, we propose a novel sampling rule called $textitG-tracking$, which uses the geometry of the context space to directly track the contexts rather than the actions.
  arXiv  Detail & Related papers  (2025-02-05T10:47:05Z)
• Fast Rates for Bandit PAC Multiclass Classification [73.17969992976501]
  We study multiclass PAC learning with bandit feedback, where inputs are classified into one of $K$ possible labels and feedback is limited to whether or not the predicted labels are correct. Our main contribution is in designing a novel learning algorithm for the agnostic $(varepsilon,delta)$PAC version of the problem.
  arXiv  Detail & Related papers  (2024-06-18T08:54:04Z)
• 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)
• Optimal Sample Complexity for Average Reward Markov Decision Processes [1.0445957451908694]
  We develop an estimator for the optimal policy of average reward MDPs with a sample complexity of $widetilde O(|S||A|t_textmix2 epsilon-2)$. This marks the first algorithm and analysis to reach the literature's lower bound.
  arXiv  Detail & Related papers  (2023-10-13T03:08:59Z)
• Stochastic Linear Bandits Robust to Adversarial Attacks [117.665995707568]
  We provide two variants of a Robust Phased Elimination algorithm, one that knows $C$ and one that does not. We show that both variants attain near-optimal regret in the non-corrupted case $C = 0$, while incurring additional additive terms respectively. In a contextual setting, we show that a simple greedy algorithm is provably robust with a near-optimal additive regret term, despite performing no explicit exploration and not knowing $C$.
  arXiv  Detail & Related papers  (2020-07-07T09:00:57Z)
• 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 Minimization in Stochastic Contextual Dueling Bandits [40.17224226373741]
  We consider the problem of $K$-armed dueling bandit in the contextual setting. We present two algorithms for the setup with respective regret guarantees.
  arXiv  Detail & Related papers  (2020-02-20T06:36:19Z)

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.