Fast Online Learning with Gaussian Prior-Driven Hierarchical Unimodal Thompson Sampling

• URL: http://arxiv.org/abs/2602.15972v1
• Date: Tue, 17 Feb 2026 19:46:00 GMT
• Title: Fast Online Learning with Gaussian Prior-Driven Hierarchical Unimodal Thompson Sampling
• Authors: Tianchi Zhao, He Liu, Hongyin Shi, Jinliang Li,
• Abstract summary: We study a type of Multi-Armed Bandit (MAB) problems in which arms with a Gaussian reward feedback are clustered.<n>Such an arm setting finds applications in many real-world problems, for example, mmWave communications and portfolio management with risky assets.
• Score: 8.624069523932372
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study a type of Multi-Armed Bandit (MAB) problems in which arms with a Gaussian reward feedback are clustered. Such an arm setting finds applications in many real-world problems, for example, mmWave communications and portfolio management with risky assets, as a result of the universality of the Gaussian distribution. Based on the Thompson Sampling algorithm with Gaussian prior (TSG) algorithm for the selection of the optimal arm, we propose our Thompson Sampling with Clustered arms under Gaussian prior (TSCG) specific to the 2-level hierarchical structure. We prove that by utilizing the 2-level structure, we can achieve a lower regret bound than we do with ordinary TSG. In addition, when the reward is Unimodal, we can reach an even lower bound on the regret by our Unimodal Thompson Sampling algorithm with Clustered Arms under Gaussian prior (UTSCG). Each of our proposed algorithms are accompanied by theoretical evaluation of the upper regret bound, and our numerical experiments confirm the advantage of our proposed algorithms.

Related papers

• Neural Dueling Bandits: Preference-Based Optimization with Human Feedback [58.90189511247936]
  We use a neural network to estimate the reward function using preference feedback for the previously selected arms.<n>We also extend our theoretical results to contextual bandit problems with binary feedback, which is in itself a non-trivial contribution.
  arXiv  Detail & Related papers  (2024-07-24T09:23:22Z)
• Bayesian Analysis of Combinatorial Gaussian Process Bandits [6.594362025904486]
  We provide novel cumulative regret bounds for three GP-based algorithms: GP-UCB, GP-BayesUCB and GP-TS.<n>We employ our framework to address the challenging real-world problem of online energy-efficient navigation.
  arXiv  Detail & Related papers  (2023-12-20T00:31:43Z)
• 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)
• Langevin Monte Carlo for Contextual Bandits [72.00524614312002]
  Langevin Monte Carlo Thompson Sampling (LMC-TS) is proposed to directly sample from the posterior distribution in contextual bandits. We prove that the proposed algorithm achieves the same sublinear regret bound as the best Thompson sampling algorithms for a special case of contextual bandits.
  arXiv  Detail & Related papers  (2022-06-22T17:58:23Z)
• Risk-Aware Algorithms for Combinatorial Semi-Bandits [7.716156977428555]
  We study the multi-armed bandit problem under semi-bandit feedback. We consider the problem of maximizing the Conditional Value-at-Risk (CVaR), a risk measure that takes into account only the worst-case rewards. We propose new algorithms that maximize the CVaR of the rewards obtained from the super arms of the bandit.
  arXiv  Detail & Related papers  (2021-12-02T11:29:43Z)
• Thompson Sampling for Bandits with Clustered Arms [7.237493755167875]
  We show, theoretically and empirically, how exploiting a given cluster structure can significantly improve the regret and computational cost. Our algorithms perform well compared to previously proposed algorithms for bandits with clustered arms.
  arXiv  Detail & Related papers  (2021-09-06T08:58:01Z)
• Batched Thompson Sampling for Multi-Armed Bandits [9.467098519620263]
  We study Thompson Sampling algorithms for multi-armed bandits in the batched setting. We propose two algorithms and demonstrate their effectiveness by experiments on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2021-08-15T20:47:46Z)
• Bayesian decision-making under misspecified priors with applications to meta-learning [64.38020203019013]
  Thompson sampling and other sequential decision-making algorithms are popular approaches to tackle explore/exploit trade-offs in contextual bandits. We show that performance degrades gracefully with misspecified priors.
  arXiv  Detail & Related papers  (2021-07-03T23:17:26Z)
• Thompson Sampling for Unimodal Bandits [21.514495320038712]
  We propose a Thompson Sampling algorithm for emphunimodal bandits, where the expected reward is unimodal over the partially ordered arms. For Gaussian rewards, the regret of our algorithm is $mathcalO(log T)$, which is far better than standard Thompson Sampling algorithms.
  arXiv  Detail & Related papers  (2021-06-15T14:40:34Z)
• Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback [51.21673420940346]
  Combinatorial bandits generalize multi-armed bandits, where the agent chooses sets of arms and observes a noisy reward for each arm contained in the chosen set. We focus on the pure-exploration problem of identifying the best arm with fixed confidence, as well as a more general setting, where the structure of the answer set differs from the one of the action set. Based on a projection-free online learning algorithm for finite polytopes, it is the first computationally efficient algorithm which is convexally optimal and has competitive empirical performance.
  arXiv  Detail & Related papers  (2021-01-21T10:35:09Z)
• Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
  We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
  arXiv  Detail & Related papers  (2020-11-18T16:40:45Z)

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.