Open access
Date
2019Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000386455Publication status
publishedExternal links
Book title
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)Journal / series
Proceedings of Machine Learning ResearchVolume
Pages / Article No.
Publisher
PMLREvent
Subject
safe learning; Optimization algorithms; uncertaintyOrganisational unit
03908 - Krause, Andreas / Krause, Andreas
09578 - Kamgarpour, Maryam (ehemalig) / Kamgarpour, Maryam (former)
More
Show all metadata
ETH Bibliography
yes
Altmetrics