paper-with-me

홈 › Papers

Distributionally Robust Bayesian Optimization with $\varphi$-divergences

2022-03-04 · NeurIPS 2023 11

The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Optimization (BO), where uncertainty is multi-faceted, yet there only exists a limited number of works dedicated to this direction. In particular, there is the work of Kirschner et al. (2020), which bridges the existing literature of Distributionally Robust Optimization (DRO) by casting the BO problem from the lens of DRO. While this work is pioneering, it admittedly suffers from various practical shortcomings such as finite contexts assumptions, leaving behind the main question Can one devise a computationally tractable algorithm for solving this DRO-BO problem? In this work, we tackle this question to a large degree of generality by considering robustness against data-shift in $\varphi$-divergences, which subsumes many popular choices, such as the $\chi^2$-divergence, Total Variation, and the extant Kullback-Leibler (KL) divergence. We show that the DRO-BO problem in this setting is equivalent to a finite-dimensional optimization problem which, even in the continuous context setting, can be easily implemented with provable sublinear regret bounds. We then show experimentally that our method surpasses existing methods, attesting to the theoretical results.

📄 PDF Abstract BibTeX arXiv:2203.02128

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Optimization

Similar Papers 제목 키워드 기반

Divergence Based Quadrangle and Applications

2023-06-28 · Anton Malandii, Siddhartha Gupte, Cheng Peng, Stan Uryasev

This paper introduces a novel framework for assessing risk and decision-making in the presence of uncertainty, the \emph{$\varphi$-Divergence Quadrangle}. This approach expands upon the traditional Risk Quadrangle, a mod…

Decision MakingManagement

Linear Time Sinkhorn Divergences using Positive Features

2020-06-12 · NeurIPS 2020 12 · Meyer Scetbon, Marco Cuturi

Although Sinkhorn divergences are now routinely used in data sciences to compare probability distributions, the computational effort required to compute them remains expensive, growing in general quadratically in the siz…

Lower Bounds on the Bayesian Risk via Information Measures

2023-03-22 · Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar

This paper focuses on parameter estimation and introduces a new method for lower bounding the Bayesian risk. The method allows for the use of virtually \emph{any} information measure, including R\'enyi's $\alpha$, $\varp…

parameter estimation

Rejection via Learning Density Ratios

2024-05-29 · Alexander Soen, Hisham Husain, Philip Schulz, Vu Nguyen

Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pipeline by augmenting typical loss functi…

Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences

2016-12-01 · NeurIPS 2016 12 · Hongseok Namkoong, John C. Duchi

We develop efficient solution methods for a robust empirical risk minimization problem designed to give calibrated confidence intervals on performance and provide optimal tradeoffs between bias and variance. Our methods …