by , , ,
Abstract:
Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is worst-case robust under a specified distributional shift of an uncontrolled covariate. In this paper, we study such a problem when the distributional shift is measured via the maximum mean discrepancy (MMD). For the setting of zeroth-order, noisy optimization, we present a novel distributionally robust Bayesian optimization algorithm (DRBO). Our algorithm provably obtains sub-linear robust regret in various settings that differ in how the uncertain covariate is observed. We demonstrate the robust performance of our method on both synthetic and real-world benchmarks.
Reference:
Distributionally Robust Bayesian Optimization J. Kirschner, I. Bogunovic, S. Jegelka, A. KrauseIn Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
Bibtex Entry:
@inproceedings{kirschner2020distributionally,
	Author = {Johannes Kirschner and Ilija Bogunovic and Stefanie Jegelka and Andreas Krause},
	Booktitle = {Proc. International Conference on Artificial Intelligence and Statistics (AISTATS)},
	Month = {June},
	Title = {Distributionally Robust Bayesian Optimization},
	Year = {2020}}