Quantum Lipschitz Bandits

• URL: http://arxiv.org/abs/2504.02251v1
• Date: Thu, 03 Apr 2025 03:39:04 GMT
• Title: Quantum Lipschitz Bandits
• Authors: Bongsoo Yi, Yue Kang, Yao Li,
• Abstract summary: Lipschitz bandit is a key variant of bandit problems where the expected reward function satisfies a Lipschitz condition.<n>We introduce the first quantum Lipschitz bandit algorithms to address the challenges of continuous action spaces and non-linear reward functions.
• Score: 6.167074802065416
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Lipschitz bandit is a key variant of stochastic bandit problems where the expected reward function satisfies a Lipschitz condition with respect to an arm metric space. With its wide-ranging practical applications, various Lipschitz bandit algorithms have been developed, achieving the cumulative regret lower bound of order $\tilde O(T^{(d_z+1)/(d_z+2)})$ over time horizon $T$. Motivated by recent advancements in quantum computing and the demonstrated success of quantum Monte Carlo in simpler bandit settings, we introduce the first quantum Lipschitz bandit algorithms to address the challenges of continuous action spaces and non-linear reward functions. Specifically, we first leverage the elimination-based framework to propose an efficient quantum Lipschitz bandit algorithm named Q-LAE. Next, we present novel modifications to the classical Zooming algorithm, which results in a simple quantum Lipschitz bandit method, Q-Zooming. Both algorithms exploit the computational power of quantum methods to achieve an improved regret bound of $\tilde O(T^{d_z/(d_z+1)})$. Comprehensive experiments further validate our improved theoretical findings, demonstrating superior empirical performance compared to existing Lipschitz bandit methods.

Related papers

• Variational Quantum Optimization with Continuous Bandits [1.6686882054452727]
  We introduce a novel approach to variational Quantum algorithms (VQA) via continuous bandits.<n>VQA are a class of hybrid Quantum-classical algorithms where the parameters of Quantum circuits are optimized by classical algorithms.
  arXiv  Detail & Related papers  (2025-02-06T12:24:30Z)
• Robustness and Generalization in Quantum Reinforcement Learning via Lipschitz Regularization [2.8445375187526154]
  We propose a regularized version of a quantum policy gradient approach, named the RegQPG algorithm. We show that training with RegQPG improves the robustness and generalization of the resulting policies.
  arXiv  Detail & Related papers  (2024-10-28T15:20:35Z)
• Quantum Bayesian Optimization [64.58749619145908]
  We introduce the quantum-Gaussian process-upper confidence bound (Q-GP-UCB) algorithm. It is the first BO algorithm able to achieve a regret upper bound of O(polylog T), which is significantly smaller than its regret lower bound of Omega(sqrt(T)) in the classical setting. Thanks to our novel analysis of the confidence ellipsoid, our Q-GP-UCB with the linear kernel achieves a smaller regret than the quantum linear UCB algorithm.
  arXiv  Detail & Related papers  (2023-10-09T03:10:42Z)
• Scalable noisy quantum circuits for biased-noise qubits [37.69303106863453]
  We consider biased-noise qubits affected only by bit-flip errors, which is motivated by existing systems of stabilized cat qubits. For realistic noise models, phase-flip will not be negligible, but in the Pauli-Twirling approximation, we show that our benchmark could check the correctness of circuits containing up to $106$ gates.
  arXiv  Detail & Related papers  (2023-05-03T11:27:50Z)
• Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning [35.11103784048256]
  We propose an textitUpper Confidence Bound (UCB) based quantum algorithmic framework to facilitate learning of a finite-horizon MDP. Our quantum algorithm achieves an exponential improvement in regret as compared to the classical counterparts.
  arXiv  Detail & Related papers  (2023-02-16T23:01:27Z)
• 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)
• Quantum Worst-Case to Average-Case Reductions for All Linear Problems [66.65497337069792]
  We study the problem of designing worst-case to average-case reductions for quantum algorithms. We provide an explicit and efficient transformation of quantum algorithms that are only correct on a small fraction of their inputs into ones that are correct on all inputs.
  arXiv  Detail & Related papers  (2022-12-06T22:01:49Z)
• Quantum Goemans-Williamson Algorithm with the Hadamard Test and Approximate Amplitude Constraints [62.72309460291971]
  We introduce a variational quantum algorithm for Goemans-Williamson algorithm that uses only $n+1$ qubits. Efficient optimization is achieved by encoding the objective matrix as a properly parameterized unitary conditioned on an auxilary qubit. We demonstrate the effectiveness of our protocol by devising an efficient quantum implementation of the Goemans-Williamson algorithm for various NP-hard problems.
  arXiv  Detail & Related papers  (2022-06-30T03:15:23Z)
• Entanglement and coherence in Bernstein-Vazirani algorithm [58.720142291102135]
  Bernstein-Vazirani algorithm allows one to determine a bit string encoded into an oracle. We analyze in detail the quantum resources in the Bernstein-Vazirani algorithm. We show that in the absence of entanglement, the performance of the algorithm is directly related to the amount of quantum coherence in the initial state.
  arXiv  Detail & Related papers  (2022-05-26T20:32:36Z)
• Quantum algorithm for stochastic optimal stopping problems with applications in finance [60.54699116238087]
  The famous least squares Monte Carlo (LSM) algorithm combines linear least square regression with Monte Carlo simulation to approximately solve problems in optimal stopping theory. We propose a quantum LSM based on quantum access to a process, on quantum circuits for computing the optimal stopping times, and on quantum techniques for Monte Carlo.
  arXiv  Detail & Related papers  (2021-11-30T12:21:41Z)
• On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory [77.18089185140767]
  Lipschitz regularity is established as a key property of modern deep learning. computing the exact value of the Lipschitz constant of a neural network is known to be NP-hard. We introduce a new upper bound for convolutional layers that is both tight and easy to compute.
  arXiv  Detail & Related papers  (2020-06-15T13:23:34Z)

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.