Error Bounds For Gaussian Process Regression Under Bounded Support Noise With Applications To Safety Certification

• URL: http://arxiv.org/abs/2408.09033v1
• Date: Fri, 16 Aug 2024 22:03:32 GMT
• Title: Error Bounds For Gaussian Process Regression Under Bounded Support Noise With Applications To Safety Certification
• Authors: Robert Reed, Luca Laurenti, Morteza Lahijanian,
• Abstract summary: We provide novel error bounds for applying Gaussian Process Regression (GPR) under bounded support noise. We show that these errors are substantially tighter than existing state-of-the-art bounds and are particularly well-suited for GPR with neural network kernels. We illustrate how these bounds can be combined with barrier functions to successfully quantify the safety probability of an unknown dynamical system.
• Score: 12.813902876908127
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gaussian Process Regression (GPR) is a powerful and elegant method for learning complex functions from noisy data with a wide range of applications, including in safety-critical domains. Such applications have two key features: (i) they require rigorous error quantification, and (ii) the noise is often bounded and non-Gaussian due to, e.g., physical constraints. While error bounds for applying GPR in the presence of non-Gaussian noise exist, they tend to be overly restrictive and conservative in practice. In this paper, we provide novel error bounds for GPR under bounded support noise. Specifically, by relying on concentration inequalities and assuming that the latent function has low complexity in the reproducing kernel Hilbert space (RKHS) corresponding to the GP kernel, we derive both probabilistic and deterministic bounds on the error of the GPR. We show that these errors are substantially tighter than existing state-of-the-art bounds and are particularly well-suited for GPR with neural network kernels, i.e., Deep Kernel Learning (DKL). Furthermore, motivated by applications in safety-critical domains, we illustrate how these bounds can be combined with stochastic barrier functions to successfully quantify the safety probability of an unknown dynamical system from finite data. We validate the efficacy of our approach through several benchmarks and comparisons against existing bounds. The results show that our bounds are consistently smaller, and that DKLs can produce error bounds tighter than sample noise, significantly improving the safety probability of control systems.

Related papers

• Robust Gaussian Processes via Relevance Pursuit [17.39376866275623]
  We propose and study a GP model that achieves robustness against sparse outliers by inferring data-point-specific noise levels. We show, surprisingly, that the model can be parameterized such that the associated log marginal likelihood is strongly concave in the data-point-specific noise variances.
  arXiv  Detail & Related papers  (2024-10-31T17:59:56Z)
• Adaptation to Misspecified Kernel Regularity in Kernelised Bandits [27.912690223941386]
  We study adaptivity to the regularity of translation-invariant kernels. It is impossible to simultaneously achieve optimal cumulative regret in a pair of RKHSs with different regularities. We connect the statistical difficulty for adaptivity in continuum-armed bandits in three fundamental types of function spaces.
  arXiv  Detail & Related papers  (2023-04-26T21:12:45Z)
• Error Bounds for Kernel-Based Linear System Identification with Unknown Hyperparameters [0.38073142980733]
  kernel-based method has been successfully applied in linear system identification using stable kernel designs. From a Gaussian process, it automatically provides probabilistic error bounds for the identified models.
  arXiv  Detail & Related papers  (2023-03-17T08:52:16Z)
• Robust Control for Dynamical Systems With Non-Gaussian Noise via Formal Abstractions [59.605246463200736]
  We present a novel controller synthesis method that does not rely on any explicit representation of the noise distributions. First, we abstract the continuous control system into a finite-state model that captures noise by probabilistic transitions between discrete states. We use state-of-the-art verification techniques to provide guarantees on the interval Markov decision process and compute a controller for which these guarantees carry over to the original control system.
  arXiv  Detail & Related papers  (2023-01-04T10:40:30Z)
• Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise [64.85879194013407]
  We prove the first high-probability results with logarithmic dependence on the confidence level for methods for solving monotone and structured non-monotone VIPs. Our results match the best-known ones in the light-tails case and are novel for structured non-monotone problems. In addition, we numerically validate that the gradient noise of many practical formulations is heavy-tailed and show that clipping improves the performance of SEG/SGDA.
  arXiv  Detail & Related papers  (2022-06-02T15:21:55Z)
• Non-Gaussian Gaussian Processes for Few-Shot Regression [71.33730039795921]
  We propose an invertible ODE-based mapping that operates on each component of the random variable vectors and shares the parameters across all of them. NGGPs outperform the competing state-of-the-art approaches on a diversified set of benchmarks and applications.
  arXiv  Detail & Related papers  (2021-10-26T10:45:25Z)
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise [59.47042225257565]
  We present a novel planning method that does not rely on any explicit representation of the noise distributions. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP)
  arXiv  Detail & Related papers  (2021-10-25T06:18:55Z)
• Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications [71.23286211775084]
  We introduce robust Gaussian process uniform error bounds in settings with unknown hyper parameters. Our approach computes a confidence region in the space of hyper parameters, which enables us to obtain a probabilistic upper bound for the model error. Experiments show that the bound performs significantly better than vanilla and fully Bayesian processes.
  arXiv  Detail & Related papers  (2021-09-06T17:10:01Z)
• A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits [91.3755431537592]
  This paper unifies the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem. Using the contraction principle in the theory of large deviations, we prove novel concentration bounds for continuous risk functionals. We show that a wide class of risk functionals as well as "nice" functions of them satisfy the continuity condition.
  arXiv  Detail & Related papers  (2021-08-25T17:09:01Z)
• Uniform Error and Posterior Variance Bounds for Gaussian Process Regression with Application to Safe Control [11.42419064387567]
  We present a novel uniform error bound using Lipschitz and an analysis of the posterior variance function for a large class of kernels. We show how these results can be used to guarantee safe control of an unknown dynamical system.
  arXiv  Detail & Related papers  (2021-01-13T20:06:30Z)

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.