Safe Convex Learning under Uncertain Constraints

arXiv1903.04626MaRDI QIDQ6315430FDOQ6315430

Authors: Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour 

Publication date: 11 March 2019

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.

This page was built for publication: Safe Convex Learning under Uncertain Constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6315430)