Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery

• URL: http://arxiv.org/abs/2402.15739v2
• Date: Thu, 4 Jul 2024 11:17:38 GMT
• Title: Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery
• Authors: Yassir Jedra, William Réveillard, Stefan Stojanovic, Alexandre Proutiere,
• Abstract summary: We present efficient algorithms for policy evaluation, best policy identification and regret minimization. For policy evaluation and best policy identification, we show that our algorithms are nearly minimax optimal. All the proposed algorithms consist of two phases: they first leverage spectral methods to estimate the left and right singular subspaces of the low-rank reward matrix.
• Score: 45.601316850669406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study contextual bandits with low-rank structure where, in each round, if the (context, arm) pair $(i,j)\in [m]\times [n]$ is selected, the learner observes a noisy sample of the $(i,j)$-th entry of an unknown low-rank reward matrix. Successive contexts are generated randomly in an i.i.d. manner and are revealed to the learner. For such bandits, we present efficient algorithms for policy evaluation, best policy identification and regret minimization. For policy evaluation and best policy identification, we show that our algorithms are nearly minimax optimal. For instance, the number of samples required to return an $\varepsilon$-optimal policy with probability at least $1-\delta$ typically scales as ${r(m+n)\over \varepsilon^2}\log(1/\delta)$. Our regret minimization algorithm enjoys minimax guarantees typically scaling as $r^{7/4}(m+n)^{3/4}\sqrt{T}$, which improves over existing algorithms. All the proposed algorithms consist of two phases: they first leverage spectral methods to estimate the left and right singular subspaces of the low-rank reward matrix. We show that these estimates enjoy tight error guarantees in the two-to-infinity norm. This in turn allows us to reformulate our problems as a misspecified linear bandit problem with dimension roughly $r(m+n)$ and misspecification controlled by the subspace recovery error, as well as to design the second phase of our algorithms efficiently.

Related papers

• Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation [48.92318828548911]
  We present LoRa-PI (Low-Rank Policy Iteration), a model-free learning algorithm alternating between policy improvement and policy evaluation steps. LoRa-PI learns an $varepsilon$-optimal policy using $widetildeO(S+Aover mathrmpoly (1-gamma)varepsilon2)$ samples where $S$ denotes the number of states (resp. actions) and $gamma$ the discount factor.
  arXiv  Detail & Related papers  (2024-10-30T20:22:17Z)
• Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path [80.60592344361073]
  We study the Shortest Path (SSP) problem with a linear mixture transition kernel. An agent repeatedly interacts with a environment and seeks to reach certain goal state while minimizing the cumulative cost. Existing works often assume a strictly positive lower bound of the iteration cost function or an upper bound of the expected length for the optimal policy.
  arXiv  Detail & Related papers  (2024-02-14T07:52:00Z)
• Best-of-Both-Worlds Algorithms for Linear Contextual Bandits [11.94312915280916]
  We study best-of-both-worlds algorithms for $K$-armed linear contextual bandits. Our algorithms deliver near-optimal regret bounds in both the adversarial and adversarial regimes.
  arXiv  Detail & Related papers  (2023-12-24T08:27:30Z)
• Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards [40.99322897009357]
  We propose two novel algorithms based on truncation and mean of medians. Our truncation-based algorithm supports online learning, distinguishing it from existing truncation-based approaches. Our algorithms improve the regret bounds by a logarithmic factor compared to existing algorithms when $epsilon=1$.
  arXiv  Detail & Related papers  (2023-10-28T13:01:10Z)
• Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR [58.40575099910538]
  We study risk-sensitive Reinforcement Learning (RL), focusing on the objective of Conditional Value at Risk (CVaR) with risk tolerance $tau$. We show the minimax CVaR regret rate is $Omega(sqrttau-1AK)$, where $A$ is the number of actions and $K$ is the number of episodes. We show that our algorithm achieves the optimal regret of $widetilde O(tau-1sqrtSAK)$ under a continuity assumption and in general attains a near
  arXiv  Detail & Related papers  (2023-02-07T02:22:31Z)
• 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)
• Variance-Aware Sparse Linear Bandits [64.70681598741417]
  Worst-case minimax regret for sparse linear bandits is $widetildeThetaleft(sqrtdTright)$. In the benign setting where there is no noise and the action set is the unit sphere, one can use divide-and-conquer to achieve an $widetildemathcal O(1)$ regret. We develop a general framework that converts any variance-aware linear bandit algorithm to a variance-aware algorithm for sparse linear bandits.
  arXiv  Detail & Related papers  (2022-05-26T15:55:44Z)
• Sketching Algorithms and Lower Bounds for Ridge Regression [65.0720777731368]
  We give a sketching-based iterative algorithm that computes $1+varepsilon$ approximate solutions for the ridge regression problem. We also show that this algorithm can be used to give faster algorithms for kernel ridge regression.
  arXiv  Detail & Related papers  (2022-04-13T22:18:47Z)
• Low-Rank Generalized Linear Bandit Problems [19.052901817304743]
  In a low-rank linear bandit problem, the reward of an action is the inner product between the action and an unknown low-rank matrix $Theta*$. We propose an algorithm based on a novel combination of online-to-confidence-set conversioncitepabbasi2012online and the exponentially weighted average forecaster constructed by a covering of low-rank matrices.
  arXiv  Detail & Related papers  (2020-06-04T15:30:14Z)

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.