by , ,
Abstract:
We address the problem of minimizing a convex smooth function f(x) over a compact polyhedral set D given a stochastic zeroth-order constraint feedback model. This problem arises in safety-critical machine learning applications, such as personalized medicine and robotics. In such cases, one needs to ensure constraints are satisfied while exploring the decision space to find optimum of the loss function. We propose a new variant of the Frank-Wolfe algorithm, which applies to the case of uncertain linear constraints. Using robust optimization, we provide the convergence rate of the algorithm while guaranteeing feasibility of all iterates, with high probability.
Reference:
Safe Convex Learning under Uncertain Constraints I. Usmanova, A. Krause, M. KamgarpourIn Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
Bibtex Entry:
@inproceedings{usmanova19safe,
	Author = {Ilnura Usmanova and Andreas Krause and Maryam Kamgarpour},
	Booktitle = {Proc. International Conference on Artificial Intelligence and Statistics (AISTATS)},
	Month = {April},
	Title = {Safe Convex Learning under Uncertain Constraints},
	Year = {2019}}