Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms

• URL: http://arxiv.org/abs/2608.14319v1
• Date: Fri, 14 Aug 2026 14:04:21 GMT
• Title: Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms
• Abstract summary: We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB)<n>We prove the first minimax lower bounds of $(Klog(T/K))$ for QMAB and $(dlog(T/d))$ for finite-action QLB.
• Score: 42.57939149964391
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB) in the model of Wan et al. [2023], where the learner queries each arm or action through a quantum reward oracle or its inverse. Prior work gives algorithms over horizon $T$ with regret $O(K\log T)$ for QMAB with $K$ arms and $O(d^2\operatorname{polylog} T)$ for $d$-dimensional QLB. This leaves open whether the $K\log T$ scale is unavoidable and whether the $d^2$ dependence can be improved. We prove the first minimax lower bounds of $Ω(K\log(T/K))$ for QMAB and $Ω(d\log(T/d))$ for finite-action QLB, resolving the question raised by Wan et al. [2023] of whether regret independent of $T$ is achievable. At the heart of our argument is a high-confidence single-arm quantum testing lower bound for distinguishing a fixed reward mean from an interval of alternatives, proved by the polynomial method and a Remez-type inequality for trigonometric polynomials. A bandit-to-testing reduction then lifts it to the QMAB lower bound, while a linear embedding gives the finite-action QLB lower bound. Complementing the lower bounds, we give a design-based elimination algorithm for finite-action QLB. When the action set has size $\operatorname{poly}(d)$, its regret is linear in $d$, improving the prior $d^2$ dependence and matching our lower bound up to polylogarithmic factors. The algorithm couples a low-bias low-variance quantum mean estimator with a small-support $G$-optimal design through a query allocation matched to the design weights. The design-based elimination reduces the dimension dependence from $d^2$ to $d^{3/2}$ when using Quantum Monte Carlo estimates. The low-variance estimator then makes reconstruction error aggregate through variance rather than worst-case absolute error, removing the remaining $\sqrt d$ factor.

Related papers

• Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise [49.730496294398726]
  We develop a novel quantum mean estimator for heavy-tailed random variables.<n>We derive stronger lower bounds for tail index>4/3$, showing that a nontrivial dependence on a dimension is unavoidable.<n>For a convex objective function, we propose a quantum projected gradient descent method.
  arXiv  Detail & Related papers  (2026-07-28T09:29:37Z)
• Approximability limits for bounded-degree max-LINSAT and implications for decoded quantum interferometry [0.0]
  For general max-k-XORSAT with $k geq 3$, no-time algorithm can do substantially better than random guessing on worst-case instances.<n>We make this connection explicit and extend the hardness to max-E$k$-LINSAT$(q,r)$ with bounded degree $D$ and over arbitrary finite fields.
  arXiv  Detail & Related papers  (2026-06-11T16:59:12Z)
• Tight inapproximability of max-LINSAT and implications for decoded quantum interferometry [0.0]
  We prove by a direct reduction from Hstad's theorem that no-time algorithm can exceed the randomassignment ratio $r/q$ by any constant.<n>This threshold coincides with the $ell/m to 0$ limit of the semicircle law governing decoded quantum interferometry.
  arXiv  Detail & Related papers  (2026-03-04T19:26:26Z)
• Quantum Heavy-tailed Bandits [36.458771174473924]
  We study multi-armed bandits (MAB) and linear bandits (SLB) with heavy-tailed rewards and quantum reward. We first propose a new quantum mean estimator for heavy-tailed distributions, which is based on the Quantum Monte Carlo Estimator. Based on our quantum mean estimator, we focus on quantum heavy-tailed MAB and SLB and propose quantum algorithms based on the Upper Confidence Bound (UCB) framework.
  arXiv  Detail & Related papers  (2023-01-23T19:23:10Z)
• 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)
• A lower bound on the space overhead of fault-tolerant quantum computation [51.723084600243716]
  The threshold theorem is a fundamental result in the theory of fault-tolerant quantum computation. We prove an exponential upper bound on the maximal length of fault-tolerant quantum computation with amplitude noise.
  arXiv  Detail & Related papers  (2022-01-31T22:19:49Z)
• Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions [53.77572276969548]
  We show that the C$2$UCB algorithm has the optimal regret bound $tildeO(dsqrtkT + dk)$ for the partition matroid constraints. For general constraints, we propose an algorithm that modifies the reward estimates of arms in the C$2$UCB algorithm.
  arXiv  Detail & Related papers  (2021-01-20T04:29:18Z)
• 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)
• Quasi-polynomial time algorithms for free quantum games in bounded dimension [11.56707165033]
  We give a semidefinite program of size $exp(mathcalObig(T12(log2(AT)+log(Q)log(AT))/epsilon2big)) to compute additive $epsilon$-approximations on the values of two-player free games. We make a connection to the quantum separability problem and employ improved multipartite quantum de Finetti theorems with linear constraints.
  arXiv  Detail & Related papers  (2020-05-18T16:55:08Z)
• Differentially Quantized Gradient Methods [53.3186247068836]
  We show that Differentially Quantized Gradient Descent (DQ-GD) attains a linear contraction factor of $maxsigma_mathrmGD, rhon 2-R$. No algorithm within a certain class can converge faster than $maxsigma_mathrmGD, 2-R$.
  arXiv  Detail & Related papers  (2020-02-06T20:40:53Z)

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.