Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration

• URL: http://arxiv.org/abs/2506.01250v1
• Date: Mon, 02 Jun 2025 01:58:48 GMT
• Title: Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration
• Authors: Youngmin Oh, Jinje Park, Taejin Paik, Jaemin Park,
• Abstract summary: We propose variance-aware algorithms that leverage neural networks to approximate nonlinear utility functions.<n>We establish theoretical guarantees showing that our algorithms achieve sublinear cumulative average regret of order $bigollt(d sqrtsum_t=1T sigma_t2 + sqrtdTrt),$ for sufficiently wide neural networks.
• Score: 6.287267171078442
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we address the contextual dueling bandit problem by proposing variance-aware algorithms that leverage neural networks to approximate nonlinear utility functions. Our approach employs a \textit{variance-aware exploration strategy}, which adaptively accounts for uncertainty in pairwise comparisons while relying only on the gradients with respect to the learnable parameters of the last layer. This design effectively balances the exploration--exploitation tradeoff under both the Upper Confidence Bound (UCB) and Thompson Sampling (TS) frameworks. As a result, under standard assumptions, we establish theoretical guarantees showing that our algorithms achieve sublinear cumulative average regret of order $\bigol\lt(d \sqrt{\sum_{t=1}^T \sigma_t^2} + \sqrt{dT}\rt),$ for sufficiently wide neural networks, where $ d $ is the contextual dimension, $ \sigma_t^2 $ the variance of comparisons at round $ t $, and $ T $ the total number of rounds. We also empirically validate that our approach offers reasonable computational efficiency and achieves sublinear regret on both synthetic tasks with nonlinear utilities and real-world tasks, outperforming existing methods.

Related papers

• 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.<n>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)
• Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits [9.877915844066338]
  A neural upper confidence bound (UCB) algorithm has shown success in contextual bandits.<n>We propose a variance-aware algorithm that utilizes $sigma2_t$, i.e., an upper bound of the reward noise variance at round $t$.<n>We provide an oracle version for our algorithm characterized by an oracle variance upper bound $sigma2_t$ and a practical version with a novel estimation for this variance bound.
  arXiv  Detail & Related papers  (2024-11-08T21:24:14Z)
• 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)
• Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency [90.40062452292091]
  We present the first computationally efficient algorithm for linear bandits with heteroscedastic noise. Our algorithm is adaptive to the unknown variance of noise and achieves an $tildeO(d sqrtsum_k = 1K sigma_k2 + d)$ regret. We also propose a variance-adaptive algorithm for linear mixture Markov decision processes (MDPs) in reinforcement learning.
  arXiv  Detail & Related papers  (2023-02-21T00:17:24Z)
• Learning Contextual Bandits Through Perturbed Rewards [107.6210145983805]
  We show that a $tildeO(tildedsqrtT)$ regret upper bound is still achievable under standard regularity conditions. We perturb the rewards when updating the neural network to eliminate the need of explicit exploration.
  arXiv  Detail & Related papers  (2022-01-24T19:10:22Z)
• Anti-Concentrated Confidence Bonuses for Scalable Exploration [57.91943847134011]
  Intrinsic rewards play a central role in handling the exploration-exploitation trade-off. We introduce emphanti-concentrated confidence bounds for efficiently approximating the elliptical bonus. We develop a practical variant for deep reinforcement learning that is competitive with contemporary intrinsic rewards on Atari benchmarks.
  arXiv  Detail & Related papers  (2021-10-21T15:25:15Z)
• Neural Contextual Bandits without Regret [47.73483756447701]
  We propose algorithms for contextual bandits harnessing neural networks to approximate the unknown reward function. We show that our approach converges to the optimal policy at a $tildemathcalO(T-1/2d)$ rate, where $d$ is the dimension of the context.
  arXiv  Detail & Related papers  (2021-07-07T11:11:34Z)
• Large-Scale Methods for Distributionally Robust Optimization [53.98643772533416]
  We prove that our algorithms require a number of evaluations gradient independent of training set size and number of parameters. Experiments on MNIST and ImageNet confirm the theoretical scaling of our algorithms, which are 9--36 times more efficient than full-batch methods.
  arXiv  Detail & Related papers  (2020-10-12T17:41:44Z)
• Neural Thompson Sampling [94.82847209157494]
  We propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network.
  arXiv  Detail & Related papers  (2020-10-02T07:44:09Z)
• Differentiable Linear Bandit Algorithm [6.849358422233866]
  Upper Confidence Bound is arguably the most commonly used method for linear multi-arm bandit problems. We introduce a gradient estimator, which allows the confidence bound to be learned via gradient ascent. We show that the proposed algorithm achieves a $tildemathcalO(hatbetasqrtdT)$ upper bound of $T$-round regret, where $d$ is the dimension of arm features and $hatbeta$ is the learned size of confidence bound.
  arXiv  Detail & Related papers  (2020-06-04T16:43:55Z)

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.