Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds

• URL: http://arxiv.org/abs/2411.12154v1
• Date: Tue, 19 Nov 2024 01:08:13 GMT
• Title: Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds
• Authors: Arda Güçlü, Subhonmesh Bose,
• Abstract summary: We propose and analyze TRAiL, a regret-optimal forced exploration algorithm for linear bandits. TraiL ensures a $Omega(sqrtT)$ growth in the inference quality, measured via the minimum eigenvalue of the design (regressor) matrix. We characterize an $Omega(sqrtT)$ minimax lower bound for any algorithm on the expected regret.
• Score: 1.03590082373586
• License:
• Abstract: We propose and analyze TRAiL (Tangential Randomization in Linear Bandits), a computationally efficient regret-optimal forced exploration algorithm for linear bandits on action sets that are sublevel sets of strongly convex functions. TRAiL estimates the governing parameter of the linear bandit problem through a standard regularized least squares and perturbs the reward-maximizing action corresponding to said point estimate along the tangent plane of the convex compact action set before projecting back to it. Exploiting concentration results for matrix martingales, we prove that TRAiL ensures a $\Omega(\sqrt{T})$ growth in the inference quality, measured via the minimum eigenvalue of the design (regressor) matrix with high-probability over a $T$-length period. We build on this result to obtain an $\mathcal{O}(\sqrt{T} \log(T))$ upper bound on cumulative regret with probability at least $ 1 - 1/T$ over $T$ periods, and compare TRAiL to other popular algorithms for linear bandits. Then, we characterize an $\Omega(\sqrt{T})$ minimax lower bound for any algorithm on the expected regret that covers a wide variety of action/parameter sets and noise processes. Our analysis not only expands the realm of lower-bounds in linear bandits significantly, but as a byproduct, yields a trade-off between regret and inference quality. Specifically, we prove that any algorithm with an $\mathcal{O}(T^\alpha)$ expected regret growth must have an $\Omega(T^{1-\alpha})$ asymptotic growth in expected inference quality. Our experiments on the $L^p$ unit ball as action sets reveal how this relation can be violated, but only in the short-run, before returning to respect the bound asymptotically. In effect, regret-minimizing algorithms must have just the right rate of inference -- too fast or too slow inference will incur sub-optimal regret growth.

Related papers

• Linear bandits with polylogarithmic minimax regret [8.97780713904412]
  We study a noise model for linear bandits for which the subgaussian noise parameter vanishes linearly as we select actions on the unit sphere closer and closer to the unknown vector. We introduce an algorithm for this problem that exhibits a minimax regret scaling as $log3(T)$ in the time horizon $T$, in stark contrast the square root scaling of this regret for typical bandit algorithms.
  arXiv  Detail & Related papers  (2024-02-19T10:56:47Z)
• 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)
• Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems [61.85150061213987]
  We study the generalized low-rank matrix bandit problem, proposed in citelu2021low under the Generalized Linear Model (GLM) framework. To overcome the computational infeasibility and theoretical restrain of existing algorithms, we first propose the G-ESTT framework. We show that G-ESTT can achieve the $tildeO(sqrt(d_1+d_2)3/2Mr3/2T)$ bound of regret while G-ESTS can achineve the $tildeO
  arXiv  Detail & Related papers  (2024-01-14T14:14:19Z)
• 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)
• Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference [23.364534479492715]
  We show that the minimum eigenvalue of the expected matrix grows as $Omega(sqrtn) whenever the expected cumulative regret of the algorithm is $sqrtn)$. We apply our result to two practical scenarios -- emphmodel selection and emphclustering in linear bandits.
  arXiv  Detail & Related papers  (2022-07-23T20:25:07Z)
• Nearly Minimax Algorithms for Linear Bandits with Shared Representation [86.79657561369397]
  We consider the setting where we play $M$ linear bandits with dimension $d$, each for $T$ rounds, and these $M$ bandit tasks share a common $k(ll d)$ dimensional linear representation. We come up with novel algorithms that achieve $widetildeOleft(dsqrtkMT + kMsqrtTright)$ regret bounds, which matches the known minimax regret lower bound up to logarithmic factors.
  arXiv  Detail & Related papers  (2022-03-29T15:27:13Z)
• Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits [45.43968161616453]
  We study the optimal batch-regret tradeoff for batch linear contextual bandits. We prove its regret guarantee, which features a two-phase expression as the time horizon $T$ grows. We also prove a new matrix inequality concentration with dependence on their dynamic upper bounds.
  arXiv  Detail & Related papers  (2021-10-15T12:32:33Z)
• Gaussian Process Bandit Optimization with Few Batches [49.896920704012395]
  We introduce a batch algorithm inspired by finite-arm bandit algorithms. We show that it achieves the cumulative regret upper bound $Oast(sqrtTgamma_T)$ using $O(loglog T)$ batches within time horizon $T$. In addition, we propose a modified version of our algorithm, and characterize how the regret is impacted by the number of batches.
  arXiv  Detail & Related papers  (2021-10-15T00:54:04Z)
• Regret Lower Bound and Optimal Algorithm for High-Dimensional Contextual Linear Bandit [10.604939762790517]
  We prove a minimax lower bound, $mathcalObig((log d)fracalpha+12Tfrac1-alpha2+log Tbig)$, for the cumulative regret. Second, we propose a simple and computationally efficient algorithm inspired by the general Upper Confidence Bound (UCB) strategy.
  arXiv  Detail & Related papers  (2021-09-23T19:35:38Z)
• Stochastic Bandits with Linear Constraints [69.757694218456]
  We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies. We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB)
  arXiv  Detail & Related papers  (2020-06-17T22:32:19Z)

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.