Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity

• URL: http://arxiv.org/abs/2410.00690v1
• Date: Tue, 1 Oct 2024 13:45:55 GMT
• Title: Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
• Authors: Quan Nguyen, Nishant A. Mehta, Cristóbal Guzmán,
• Abstract summary: We show a novel notion of sparsity that we dub $(lambda, beta)$-sparsity. We also show an adaptive algorithm which adapts to the best $(lambda, beta)$-sparsity condition that holds.
• Score: 14.396304498754688
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The minimax sample complexity of group distributionally robust optimization (GDRO) has been determined up to a $\log(K)$ factor, for $K$ the number of groups. In this work, we venture beyond the minimax perspective via a novel notion of sparsity that we dub $(\lambda, \beta)$-sparsity. In short, this condition means that at any parameter $\theta$, there is a set of at most $\beta$ groups whose risks at $\theta$ all are at least $\lambda$ larger than the risks of the other groups. To find an $\epsilon$-optimal $\theta$, we show via a novel algorithm and analysis that the $\epsilon$-dependent term in the sample complexity can swap a linear dependence on $K$ for a linear dependence on the potentially much smaller $\beta$. This improvement leverages recent progress in sleeping bandits, showing a fundamental connection between the two-player zero-sum game optimization framework for GDRO and per-action regret bounds in sleeping bandits. The aforementioned result assumes having a particular $\lambda$ as input. Perhaps surprisingly, we next show an adaptive algorithm which, up to log factors, gets sample complexity that adapts to the best $(\lambda, \beta)$-sparsity condition that holds. Finally, for a particular input $\lambda$, we also show how to get a dimension-free sample complexity result.

Related papers

• 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)
• 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)
• Context-lumpable stochastic bandits [49.024050919419366]
  We consider a contextual bandit problem with $S$ contexts and $K$ actions. We give an algorithm that outputs an $epsilon$-optimal policy after using at most $widetilde O(r (S +K )/epsilon2)$ samples. In the regret setting, we give an algorithm whose cumulative regret up to time $T$ is bounded by $widetilde O(sqrtr3(S+K)T)$.
  arXiv  Detail & Related papers  (2023-06-22T17:20:30Z)
• Asymptotically Optimal Pure Exploration for Infinite-Armed Bandits [4.811176167998627]
  We study pure exploration with infinitely many bandit arms generated i.i.d. from an unknown distribution. Our goal is to efficiently select a single high quality arm whose average reward is, with probability $1-delta$, within $varepsilon$ of being among the top $eta$-fraction of arms.
  arXiv  Detail & Related papers  (2023-06-03T04:00:47Z)
• Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes [62.90204655228324]
  We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic and a value-optimistic solver.
  arXiv  Detail & Related papers  (2022-10-20T21:32:01Z)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Streaming Complexity of SVMs [110.63976030971106]
  We study the space complexity of solving the bias-regularized SVM problem in the streaming model. We show that for both problems, for dimensions of $frac1lambdaepsilon$, one can obtain streaming algorithms with spacely smaller than $frac1lambdaepsilon$.
  arXiv  Detail & Related papers  (2020-07-07T17:10:00Z)
• Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners [17.224805430291177]
  We study the problem of best arm identification in linearly parameterised multi-armed bandits. We propose an explicitly implementable and provably order-optimal sample-complexity algorithm to solve this problem.
  arXiv  Detail & Related papers  (2020-06-13T05:00:01Z)
• Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity [59.34067736545355]
  Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy. For small enough $epsilon$, we show an improved algorithm with sample complexity.
  arXiv  Detail & Related papers  (2020-06-06T13:34:41Z)

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.