On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise

• URL: http://arxiv.org/abs/2412.18789v1
• Date: Wed, 25 Dec 2024 05:57:27 GMT
• Title: On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise
• Authors: Jingyi Wang, Haowei Wang, Cosmin G. Petra, Nai-Yuan Chiang,
• Abstract summary: convergence analysis of BO algorithms has focused on the cumulative regret under both the Bayesian and frequentist settings for the objective. We establish new pointwise on the prediction error of GP under the frequentist setting with Gaussian noise. We prove improved convergence rates of cumulative regret bound for both GP-UCB and GP-TS.
• Score: 2.250251490529229
• License:
• Abstract: Bayesian optimization (BO) with Gaussian process (GP) surrogate models is a powerful black-box optimization method. Acquisition functions are a critical part of a BO algorithm as they determine how the new samples are selected. Some of the most widely used acquisition functions include upper confidence bound (UCB) and Thompson sampling (TS). The convergence analysis of BO algorithms has focused on the cumulative regret under both the Bayesian and frequentist settings for the objective. In this paper, we establish new pointwise bounds on the prediction error of GP under the frequentist setting with Gaussian noise. Consequently, we prove improved convergence rates of cumulative regret bound for both GP-UCB and GP-TS. Of note, the new prediction error bound under Gaussian noise can be applied to general BO algorithms and convergence analysis, e.g., the asymptotic convergence of expected improvement (EI) with noise.

Related papers

• Regret Analysis for Randomized Gaussian Process Upper Confidence Bound [9.967062483758632]
  This paper analyzes the randomized variant of GP-UCB called improved randomized GP-UCB. In both regret analyses, IRGP-UCB achieves a sub-linear regret upper bound without increasing the confidence parameter if the input domain is finite.
  arXiv  Detail & Related papers  (2024-09-02T06:49:29Z)
• Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration [2.984929040246293]
  novel noise-free Bayesian optimization strategies that rely on a random exploration step to enhance the accuracy of Gaussian process surrogate models. New algorithms retain the ease of implementation of the classical GP-UCB, but an additional exploration step facilitates their convergence.
  arXiv  Detail & Related papers  (2024-01-30T14:16:06Z)
• A Corrected Expected Improvement Acquisition Function Under Noisy Observations [22.63212972670109]
  Sequential of expected improvement (EI) is one of the most widely used policies in Bayesian optimization. The uncertainty associated with the incumbent solution is often neglected in many analytic EI-type methods. We propose a modification of EI that corrects its closed-form expression by incorporating the covariance information provided by the Gaussian Process (GP) model.
  arXiv  Detail & Related papers  (2023-10-08T13:50:39Z)
• Batch Bayesian optimisation via density-ratio estimation with guarantees [26.052368583196426]
  We present a theoretical analysis of BORE's regret and an extension of the algorithm with improved uncertainty estimates. We also show that BORE can be naturally extended to a batch optimisation setting by recasting the problem as approximate Bayesian inference.
  arXiv  Detail & Related papers  (2022-09-22T00:42:18Z)
• Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization [63.8557841188626]
  The expected improvement (EI) algorithm is one of the most popular strategies for optimization under uncertainty. We propose a variant of EI with a standard incumbent defined via the GP predictive mean. We show that our algorithm converges, and achieves a cumulative regret bound of $mathcal O(gamma_TsqrtT)$.
  arXiv  Detail & Related papers  (2022-03-15T13:17:53Z)
• Misspecified Gaussian Process Bandit Optimization [59.30399661155574]
  Kernelized bandit algorithms have shown strong empirical and theoretical performance for this problem. We introduce a emphmisspecified kernelized bandit setting where the unknown function can be $epsilon$--uniformly approximated by a function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS) We show that our algorithm achieves optimal dependence on $epsilon$ with no prior knowledge of misspecification.
  arXiv  Detail & Related papers  (2021-11-09T09:00:02Z)
• No-Regret Algorithms for Time-Varying Bayesian Optimization [0.0]
  We adopt the general variation budget model to capture the time-varying environment. We introduce two GP-UCB type algorithms: R-GP-UCB and SW-GP-UCB, respectively. Our results not only recover previous linear bandit results when a linear kernel is used, but complement the previous regret analysis of time-varying Gaussian process bandit.
  arXiv  Detail & Related papers  (2021-02-11T22:35:32Z)
• Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
  We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
  arXiv  Detail & Related papers  (2020-11-18T16:40:45Z)
• Convergence of adaptive algorithms for weakly convex constrained optimization [59.36386973876765]
  We prove the $mathcaltilde O(t-1/4)$ rate of convergence for the norm of the gradient of Moreau envelope. Our analysis works with mini-batch size of $1$, constant first and second order moment parameters, and possibly smooth optimization domains.
  arXiv  Detail & Related papers  (2020-06-11T17:43:19Z)
• Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation [60.93091603232817]
  We develop a modified Gaussian process upper confidence bound (GP-UCB) acquisition function. This is done by sampling the exploration-exploitation trade-off parameter from a distribution. We prove that this allows the expected trade-off parameter to be altered to better suit the problem without compromising a bound on the function's Bayesian regret.
  arXiv  Detail & Related papers  (2020-06-08T00:28:41Z)
• Global Optimization of Gaussian processes [52.77024349608834]
  We propose a reduced-space formulation with trained Gaussian processes trained on few data points. The approach also leads to significantly smaller and computationally cheaper sub solver for lower bounding. In total, we reduce time convergence by orders of orders of the proposed method.
  arXiv  Detail & Related papers  (2020-05-21T20:59:11Z)

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.