AISTATS 2019poster56 citations
Safe Convex Learning under Uncertain Constraints
Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour
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.
BibTeX
@InProceedings{pmlr-v89-usmanova19a,
title = {Safe Convex Learning under Uncertain Constraints},
author = {Usmanova, Ilnura and Krause, Andreas and Kamgarpour, Maryam},
booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics},
pages = {2106--2114},
year = {2019},
editor = {Chaudhuri, Kamalika and Sugiyama, Masashi},
volume = {89},
series = {Proceedings of Machine Learning Research},
month = {16--18 Apr},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v89/usmanova19a/usmanova19a.pdf},
url = {https://proceedings.mlr.press/v89/usmanova19a.html},
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.}
}