Leveraging Offline Data in Linear Latent Contextual Bandits

• URL: http://arxiv.org/abs/2405.17324v2
• Date: Tue, 02 Sep 2025 02:16:56 GMT
• Title: Leveraging Offline Data in Linear Latent Contextual Bandits
• Authors: Chinmaya Kausik, Kevin Tan, Ambuj Tewari,
• Abstract summary: We design end-to-end latent bandit algorithms capable of handing uncountably many latent states.<n>We present two online algorithms that utilize the output of this offline algorithm to accelerate online learning.
• Score: 27.272915631913175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Leveraging offline data is an attractive way to accelerate online sequential decision-making. However, it is crucial to account for latent states in users or environments in the offline data, and latent bandits form a compelling model for doing so. In this light, we design end-to-end latent bandit algorithms capable of handing uncountably many latent states. We focus on a linear latent contextual bandit $-$ a linear bandit where each user has its own high-dimensional reward parameter in $\mathbb{R}^{d_A}$, but reward parameters across users lie in a low-rank latent subspace of dimension $d_K \ll d_A$. First, we provide an offline algorithm to learn this subspace with provable guarantees. We then present two online algorithms that utilize the output of this offline algorithm to accelerate online learning. The first enjoys $\tilde{O}(\min(d_A\sqrt{T}, d_K\sqrt{T}(1+\sqrt{d_AT/d_KN})))$ regret guarantees, so that the effective dimension is lower when the size $N$ of the offline dataset is larger. We prove a matching lower bound on regret, showing that our algorithm is minimax optimal. The second is a practical algorithm that enjoys only a slightly weaker guarantee, but is computationally efficient. We also establish the efficacy of our methods using experiments on both synthetic data and real-life movie recommendation data from MovieLens. Finally, we theoretically establish the generality of the latent bandit model by proving a de Finetti theorem for stateless decision processes.

Related papers

• Regret minimization in Linear Bandits with offline data via extended D-optimal exploration [25.533340168328564]
  We consider the problem of online regret in linear bandits with access to prior observations (offline data) from the underlying bandit model.<n>Our algorithm, Offline-Online Phased Elimination (OOPE), effectively incorporates the offline data to substantially reduce the online regret compared to prior work.
  arXiv  Detail & Related papers  (2025-08-11T19:14:56Z)
• Online Learning with Probing for Sequential User-Centric Selection [8.45399786458738]
  We present a probing-augmented user-centric selection (PUCS) framework, where a learner first probes a subset of arms to obtain side information on resources and rewards, and then assigns $K$ plays to $M$ arms.<n>For the offline setting with known distributions, we present a greedy probing algorithm with a constant-factor approximation guarantee $zeta = (e-1)/ (2e-1)$.<n>For the online setting with unknown distributions, we introduce OLPA, a bandit algorithm that a regret a bound $mathcalO(sqrtT +
  arXiv  Detail & Related papers  (2025-07-27T03:32:51Z)
• Regret Minimization and Statistical Inference in Online Decision Making with High-dimensional Covariates [7.21848268647674]
  We integrate the $varepsilon$-greedy bandit algorithm for decision-making with a hard thresholding algorithm for estimating sparse bandit parameters. Under a margin condition, our method achieves either $O(T1/2)$ regret or classical $O(T1/2)$-consistent inference.
  arXiv  Detail & Related papers  (2024-11-10T01:47:11Z)
• Sparse Linear Bandits with Blocking Constraints [22.01704171400845]
  We investigate the high-dimensional sparse linear bandits problem in a data-poor regime.<n>We show novel offline statistical guarantees of the lasso estimator for the linear model.<n>We propose a meta-algorithm based on corralling that does not need knowledge of optimal sparsity parameter $k$ at minimal cost to regret.
  arXiv  Detail & Related papers  (2024-10-26T01:42:03Z)
• Indexed Minimum Empirical Divergence-Based Algorithms for Linear Bandits [55.938644481736446]
  Indexed Minimum Empirical Divergence (IMED) is a highly effective approach to the multi-armed bandit problem. It has been observed to empirically outperform UCB-based algorithms and Thompson Sampling. We present novel linear versions of the IMED algorithm, which we call the family of LinIMED algorithms.
  arXiv  Detail & Related papers  (2024-05-24T04:11:58Z)
• When is Agnostic Reinforcement Learning Statistically Tractable? [76.1408672715773]
  A new complexity measure, called the emphspanning capacity, depends solely on the set $Pi$ and is independent of the MDP dynamics. We show there exists a policy class $Pi$ with a bounded spanning capacity that requires a superpolynomial number of samples to learn. This reveals a surprising separation for learnability between generative access and online access models.
  arXiv  Detail & Related papers  (2023-10-09T19:40:54Z)
• Anytime Model Selection in Linear Bandits [61.97047189786905]
  We develop ALEXP, which has an exponentially improved dependence on $M$ for its regret. Our approach utilizes a novel time-uniform analysis of the Lasso, establishing a new connection between online learning and high-dimensional statistics.
  arXiv  Detail & Related papers  (2023-07-24T15:44:30Z)
• Optimal Best-Arm Identification in Bandits with Access to Offline Data [27.365122983434887]
  We consider combining offline data with online learning, an area less studied but obvious practical importance. We develop algorithms that match the lower bound on sample complexity when $delta$ is small. Our algorithms are computationally efficient with an average per-sample acquisition cost of $tildeO(K)$, and rely on a careful characterization of the optimality conditions of the lower bound problem.
  arXiv  Detail & Related papers  (2023-06-15T11:12:35Z)
• On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits [76.2262680277608]
  We study linear contextual bandits in the misspecified setting, where the expected reward function can be approximated by a linear function class. We show that our algorithm enjoys the same gap-dependent regret bound $tilde O (d2/Delta)$ as in the well-specified setting up to logarithmic factors.
  arXiv  Detail & Related papers  (2023-03-16T15:24:29Z)
• Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards [33.88533898709351]
  VIPeR amalgamates the randomized value function idea with the pessimism principle. It implicitly obtains pessimism by simply perturbing the offline data multiple times. It is both provably and computationally efficient in general Markov decision processes (MDPs) with neural network function approximation.
  arXiv  Detail & Related papers  (2023-02-24T17:52:12Z)
• On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation [80.86358123230757]
  We present an algorithm called Bootstrapped and Constrained Pessimistic Value Iteration (BCP-VI) Under a partial data coverage assumption, BCP-VI yields a fast rate of $tildemathcalO(frac1K)$ for offline RL when there is a positive gap in the optimal Q-value functions. These are the first $tildemathcalO(frac1K)$ bound and absolute zero sub-optimality bound respectively for offline RL with linear function approximation from adaptive data.
  arXiv  Detail & Related papers  (2022-11-23T18:50:44Z)
• Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes [99.26864533035454]
  We study offline reinforcement learning (RL) in partially observable Markov decision processes. We propose the underlineProxy variable underlinePessimistic underlinePolicy underlineOptimization (textttP3O) algorithm. textttP3O is the first provably efficient offline RL algorithm for POMDPs with a confounded dataset.
  arXiv  Detail & Related papers  (2022-05-26T19:13:55Z)
• Efficient Online Bayesian Inference for Neural Bandits [10.353171848879187]
  We present a new algorithm for online (sequential) inference in Bayesian neural networks. The key idea is to combine the extended Kalman filter with a subspace for the parameters. We show good results on the "Deep Bayesian Bandit Showdown" benchmark, as well as MNIST and a recommender system.
  arXiv  Detail & Related papers  (2021-12-01T00:29:51Z)
• Online Sparse Reinforcement Learning [60.44832065993122]
  We investigate the hardness of online reinforcement learning in fixed horizon, sparse linear decision process (MDP) We show that linear regret is generally unavoidable in this case, even if there exists a policy that collects well-conditioned data. This shows that in the large-action setting, the difficulty of learning can be attributed to the difficulty of finding a good exploratory policy.
  arXiv  Detail & Related papers  (2020-11-08T16:47:42Z)
• Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits [61.490254407420906]
  We study the online restless bandit problem, where the state of each arm evolves according to a Markov chain. We propose Restless-UCB, a learning policy that follows the explore-then-commit framework.
  arXiv  Detail & Related papers  (2020-11-05T05:16:04Z)
• Impact of Representation Learning in Linear Bandits [83.17684841392754]
  We study how representation learning can improve the efficiency of bandit problems. We present a new algorithm which achieves $widetildeO(TsqrtkN + sqrtdkNT)$ regret, where $N$ is the number of rounds we play for each bandit.
  arXiv  Detail & Related papers  (2020-10-13T16:35:30Z)
• Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selection [71.9765117768556]
  We consider the contextual bandit problem under the high dimensional linear model. This setting finds essential applications such as personalized recommendation, online advertisement, and personalized medicine. We propose doubly growing epochs and estimating the parameter using the best subset selection method.
  arXiv  Detail & Related papers  (2020-09-04T04:10:39Z)
• Latent Bandits Revisited [55.88616813182679]
  A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. We propose general algorithms for this setting, based on both upper confidence bounds (UCBs) and Thompson sampling. We provide a unified theoretical analysis of our algorithms, which have lower regret than classic bandit policies when the number of latent states is smaller than actions.
  arXiv  Detail & Related papers  (2020-06-15T19:24:02Z)
• An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling [83.48992319018147]
  We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. A natural way to resolve this problem is to apply online gradient descent (SGD) so that the per-step time and memory complexity can be reduced to constant. In this work, we show that online SGD can be applied to the generalized linear bandit problem. The proposed SGD-TS algorithm, which uses a single-step SGD update to exploit past information, achieves $tildeO(sqrtT)$ regret with the total time complexity that
  arXiv  Detail & Related papers  (2020-06-07T01:12:39Z)

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.