PACSBO: Probably approximately correct safe Bayesian optimization

• URL: http://arxiv.org/abs/2409.01163v1
• Date: Mon, 2 Sep 2024 10:50:34 GMT
• Title: PACSBO: Probably approximately correct safe Bayesian optimization
• Authors: Abdullah Tokmak, Thomas B. Schön, Dominik Baumann,
• Abstract summary: We propose an algorithm that estimates an upper bound on the RKHS norm of an unknown function from data. We treat the RKHS norm as a local rather than a global object, and thus reduce conservatism. Integrating the RKHS norm estimation and the local interpretation of the RKHS norm into a safe BO algorithm yields PACSBO.
• Score: 10.487548576958421
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safe Bayesian optimization (BO) algorithms promise to find optimal control policies without knowing the system dynamics while at the same time guaranteeing safety with high probability. In exchange for those guarantees, popular algorithms require a smoothness assumption: a known upper bound on a norm in a reproducing kernel Hilbert space (RKHS). The RKHS is a potentially infinite-dimensional space, and it is unclear how to, in practice, obtain an upper bound of an unknown function in its corresponding RKHS. In response, we propose an algorithm that estimates an upper bound on the RKHS norm of an unknown function from data and investigate its theoretical properties. Moreover, akin to Lipschitz-based methods, we treat the RKHS norm as a local rather than a global object, and thus reduce conservatism. Integrating the RKHS norm estimation and the local interpretation of the RKHS norm into a safe BO algorithm yields PACSBO, an algorithm for probably approximately correct safe Bayesian optimization, for which we provide numerical and hardware experiments that demonstrate its applicability and benefits over popular safe BO algorithms.

Related papers

• On Safety in Safe Bayesian Optimization [5.9045432488022485]
  We investigate three safety-related issues of the popular class of SafeOpt-type algorithms. First, these algorithms critically rely on frequentist bounds uncertainty for Gaussian Process (GP) regression. Second, we identify assuming an upper bound on the reproducing kernel Hilbert space (RKHS) norm of the target function. Third, SafeOpt and derived algorithms rely on a discrete search space, making them difficult to apply to higher-dimensional problems.
  arXiv  Detail & Related papers  (2024-03-19T17:50:32Z)
• Information-Theoretic Safe Bayesian Optimization [59.758009422067005]
  We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an unknown (safety) constraint. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. We propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
  arXiv  Detail & Related papers  (2024-02-23T14:31:10Z)
• Bayesian Optimization with Formal Safety Guarantees via Online Conformal Prediction [36.14499894307206]
  Black-box zero-th order optimization is a central primitive for applications in fields as diverse as finance, physics, and engineering. In this paper, we study scenarios in which feedback is also provided on the safety of the attempted solution. A novel BO-based approach is introduced that satisfies safety requirements irrespective of properties of the constraint function.
  arXiv  Detail & Related papers  (2023-06-30T17:26:49Z)
• 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)
• Meta-Learning Hypothesis Spaces for Sequential Decision-making [79.73213540203389]
  We propose to meta-learn a kernel from offline data (Meta-KeL) Under mild conditions, we guarantee that our estimated RKHS yields valid confidence sets. We also empirically evaluate the effectiveness of our approach on a Bayesian optimization task.
  arXiv  Detail & Related papers  (2022-02-01T17:46:51Z)
• 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)
• Safe Policy Optimization with Local Generalized Linear Function Approximations [17.84511819022308]
  Existing safe exploration methods guaranteed safety under the assumption of regularity. We propose a novel algorithm, SPO-LF, that optimize an agent's policy while learning the relation between a locally available feature obtained by sensors and environmental reward/safety. We experimentally show that our algorithm is 1) more efficient in terms of sample complexity and computational cost and 2) more applicable to large-scale problems than previous safe RL methods with theoretical guarantees.
  arXiv  Detail & Related papers  (2021-11-09T00:47:50Z)
• Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces [63.22864716473051]
  We propose a novel BO algorithm which expands (and shifts) the search space over iterations. We show theoretically that for both our algorithms, the cumulative regret grows at sub-linear rates.
  arXiv  Detail & Related papers  (2020-09-05T14:24:40Z)
• Corruption-Tolerant Gaussian Process Bandit Optimization [130.60115798580136]
  We consider the problem of optimizing an unknown (typically non-producing) function with a bounded norm. We introduce an algorithm based on Fast-Slow GP-UCB based on "fast but non-robust" and "slow" We argue that certain dependencies cannot be required depending on the corruption level.
  arXiv  Detail & Related papers  (2020-03-04T09:46:58Z)

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.