Active learning for distributionally robust level-set estimation

Many cases exist in which a black-box function f with high evaluation cost depends on two types of variables x and w, where x is a controllable design variable and w are uncontrollable environmental variables that have random variation following a certain distribution P . In such cases, an important task is to find the range of design variables x such that the function f(x,w) has the desired properties by incorporating the random variation of the environmental variables w. A natural measure of robustness is the probability that f(x,w) exceeds a given threshold h, which is known as the probability threshold robustness (PTR) measure in the literature on robust optimization. However, this robustness measure cannot be correctly evaluated when the distribution P is unknown. In this study, we addressed this problem by considering the distributionally robust PTR (DRPTR) measure, which considers the worst-case PTR within given candidate distributions. Specifically, we studied the problem of efficiently identifying a reliable set H, which is defined as a region in which the DRPTR measure exceeds a certain desired probability α, which can be interpreted as a level set estimation (LSE) problem for DRPTR. We propose a theoretically grounded and computationally efficient active learning method for this problem. We show that the proposed method has theoretical guarantees on convergence and accuracy, and confirmed through numerical experiments that the proposed method outperforms existing methods.

[1]  Christian Daniel,et al.  Noisy-Input Entropy Search for Efficient Robust Bayesian Optimization , 2020, AISTATS.

[2]  Peter I. Frazier,et al.  Bayesian Optimization with Expensive Integrands , 2018, SIAM J. Optim..

[3]  W. O. Kermack,et al.  A contribution to the mathematical theory of epidemics , 1927 .

[4]  Johannes Kirschner,et al.  Distributionally Robust Bayesian Optimization , 2020, AISTATS.

[5]  Alkis Gotovos,et al.  Active Learning for Level Set Estimation , 2022 .

[6]  Y. Z. Mehrjerdi.  A Chance Constrained Programming , 2012 .

[7]  Bernhard Sendhoff,et al.  Robust Optimization - A Comprehensive Survey , 2007 .

[8]  Volkan Cevher,et al.  Adversarially Robust Optimization with Gaussian Processes , 2018, NeurIPS.

[9]  Ichiro Takeuchi,et al.  Active Learning for Level Set Estimation Under Input Uncertainty and Its Extensions , 2020, Neural Computation.

[10]  Ichiro Takeuchi,et al.  Bayesian Experimental Design for Finding Reliable Level Set Under Input Uncertainty , 2019, IEEE Access.

[11]  Nando de Freitas,et al.  Taking the Human Out of the Loop: A Review of Bayesian Optimization , 2016, Proceedings of the IEEE.

[12]  Javier González,et al.  Active Multi-Information Source Bayesian Quadrature , 2019, UAI.

[13]  Ichiro Takeuchi,et al.  Bayesian Quadrature Optimization for Probability Threshold Robustness Measure , 2020, Neural Computation.

[14]  Justin J. Beland.  Bayesian Optimization Under Uncertainty , 2017 .

[15]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[16]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[17]  Fabio Tozeto Ramos,et al.  Bayesian optimisation under uncertain inputs , 2019, AISTATS.

[18]  Joel W. Burdick,et al.  Stagewise Safe Bayesian Optimization with Gaussian Processes , 2018, ICML.

[19]  S. Vaida,et al.  Studies in the Mathematical Theory of Inventory and Production , 1958 .

[20]  Andreas Krause,et al.  Safe Exploration in Finite Markov Decision Processes with Gaussian Processes , 2016, NIPS.

[21]  Larry A. Wasserman,et al.  Active Learning For Identifying Function Threshold Boundaries , 2005, NIPS.

[22]  HighWire Press.  Proceedings of the Royal Society of London. Series A, Containing papers of a mathematical and physical character , 1934 .

[23]  Ichiro Takeuchi,et al.  Active Learning of Bayesian Linear Models with High-Dimensional Binary Features by Parameter Confidence-Region Estimation , 2020, Neural Computation.

[24]  Santu Rana,et al.  Distributionally Robust Bayesian Quadrature Optimization , 2020, AISTATS.

[25]  Ichiro Takeuchi,et al.  Active Learning for Enumerating Local Minima Based on Gaussian Process Derivatives , 2019, Neural Computation.

[26]  Herbert E. Scarf,et al.  A Min-Max Solution of an Inventory Problem , 1957 .

[27]  Mykel J. Kochenderfer,et al.  Robust Super-Level Set Estimation using Gaussian Processes , 2018, ECML/PKDD.

[28]  Sanjay Mehrotra,et al.  Distributionally Robust Optimization: A Review , 2019, ArXiv.

[29]  Alkis Gotovos,et al.  Safe Exploration for Optimization with Gaussian Processes , 2015, ICML.

[30]  Yisong Yue,et al.  Safe Exploration and Optimization of Constrained MDPs Using Gaussian Processes , 2018, AAAI.

[31]  Ichiro Takeuchi,et al.  Mean-Variance Analysis in Bayesian Optimization under Uncertainty , 2020, AISTATS.

[32]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.