Maximally Robust Satisficing Bayesian Optimization

• URL: http://arxiv.org/abs/2607.13652v1
• Date: Wed, 15 Jul 2026 09:53:18 GMT
• Title: Maximally Robust Satisficing Bayesian Optimization
• Abstract summary: We show that robustness to input perturbations that may occur when the solution is deployed is a good criterion.<n>We introduce a Bayesian optimization method that efficiently finds satisficing solutions that are robust to maximally large perturbations.
• Score: 6.436428314037097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many design tasks can be cast as black-box function optimization, enabling use of Bayesian optimization to find an ideal design with minimal number of trials. However, often we do not actually need the optimum but instead a sufficiently good solution is enough, for instance a material that is durable enough for its intended use. In most cases there are multiple satisfactory solutions, forming a superlevel set of the function, raising a key question of which one to prefer. We answer this by explaining why robustness to input perturbations that may occur when the solution is deployed is a good criterion and by introduce a Bayesian optimization method that efficiently finds satisficing solutions that are robust to maximally large perturbations. In contrast to previous works, we assume the inputs can be accurately controlled during optimization, but will be perturbed after the deployment.

Related papers

• Optimizing Optimizers for Fast Gradient-Based Learning [53.81268610971847]
  We lay the theoretical foundation for automating design in gradient-based learning.<n>By treating gradient loss signals as a function that translates to parameter motions, the problem reduces to a family of convex optimization problems.
  arXiv  Detail & Related papers  (2025-12-06T09:50:41Z)
• An Analysis of Safety Guarantees in Multi-Task Bayesian Optimization [1.534667887016089]
  This paper addresses the integration of additional information sources into a Bayesian optimization framework.<n>The interdependencies between these information sources are modeled using an unknown correlation matrix.<n>We explore how uniform error bounds must be adjusted to maintain constraint satisfaction throughout the optimization process.
  arXiv  Detail & Related papers  (2025-03-11T15:45:37Z)
• A Novel Unified Parametric Assumption for Nonconvex Optimization [53.943470475510196]
  Non optimization is central to machine learning, but the general framework non convexity enables weak convergence guarantees too pessimistic compared to the other hand.<n>We introduce a novel unified assumption in non convex algorithms.
  arXiv  Detail & Related papers  (2025-02-17T21:25:31Z)
• Learning Multiple Initial Solutions to Optimization Problems [52.9380464408756]
  Sequentially solving similar optimization problems under strict runtime constraints is essential for many applications.<n>We propose learning to predict emphmultiple diverse initial solutions given parameters that define the problem instance.<n>We find significant and consistent improvement with our method across all evaluation settings and demonstrate that it efficiently scales with the number of initial solutions required.
  arXiv  Detail & Related papers  (2024-11-04T15:17:19Z)
• Optimization on Pareto sets: On a theory of multi-objective optimization [7.907376287850398]
  In multi-objective optimization, a single decision vector must balance the trade-offs between many objectives. We consider a more practically significant optimization problem, where the goal is to optimize a constrained set.
  arXiv  Detail & Related papers  (2023-08-04T05:55:52Z)
• Optimistic Optimization of Gaussian Process Samples [30.226274682578172]
  A competing, computationally more efficient, global optimization framework is optimistic optimization, which exploits prior knowledge about the geometry of the search space in form of a dissimilarity function. We argue that there is a new research domain between geometric and probabilistic search, i.e. methods that run drastically faster than traditional Bayesian optimization, while retaining some of the crucial functionality of Bayesian optimization.
  arXiv  Detail & Related papers  (2022-09-02T09:06:24Z)
• Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares [68.8204255655161]
  We consider potentially non- optimized approximation problems. In this paper, we propose an algorithm that achieves close to optimal a priori computational guarantees.
  arXiv  Detail & Related papers  (2022-04-11T09:37:04Z)
• A Robust Multi-Objective Bayesian Optimization Framework Considering Input Uncertainty [0.0]
  In real-life applications like engineering design, the designer often wants to take multiple objectives as well as input uncertainty into account. We introduce a novel Bayesian optimization framework to efficiently perform multi-objective optimization considering input uncertainty.
  arXiv  Detail & Related papers  (2022-02-25T17:45:26Z)
• Bayesian Optimization for Min Max Optimization [77.60508571062958]
  We propose algorithms that perform Min Max Optimization in a setting where the function that should be optimized is not known a priori. We extend the two acquisition functions Expected Improvement and Gaussian Process Upper Confidence Bound. We show that these acquisition functions allow for better solutions - converging faster to the optimum than the benchmark settings.
  arXiv  Detail & Related papers  (2021-07-29T06:49:34Z)
• Uncertainty aware Search Framework for Multi-Objective Bayesian Optimization with Constraints [44.25245545568633]
  We consider the problem of constrained multi-objective (MO) blackbox optimization using expensive function evaluations. We propose a novel framework named Uncertainty-aware Search framework for Multi-Objective Optimization with Constraints. We show that USeMOC is able to achieve more than 90 % reduction in the number of simulations needed to uncover optimized circuits.
  arXiv  Detail & Related papers  (2020-08-16T23:34:09Z)
• Incorporating Expert Prior in Bayesian Optimisation via Space Warping [54.412024556499254]
  In big search spaces the algorithm goes through several low function value regions before reaching the optimum of the function. One approach to subside this cold start phase is to use prior knowledge that can accelerate the optimisation. In this paper, we represent the prior knowledge about the function optimum through a prior distribution. The prior distribution is then used to warp the search space in such a way that space gets expanded around the high probability region of function optimum and shrinks around low probability region of optimum.
  arXiv  Detail & Related papers  (2020-03-27T06:18:49Z)

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.