Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case AV Gasnikov, EA Krymova, AA Lagunovskaya, IN Usmanova, ... Automation and remote control 78, 224-234, 2017 | 66 | 2017 |
Safe convex learning under uncertain constraints I Usmanova, A Krause, M Kamgarpour The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 45 | 2019 |
Constrained policy optimization via bayesian world models Y As, I Usmanova, S Curi, A Krause arXiv preprint arXiv:2201.09802, 2022 | 43 | 2022 |
Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex AV Gasnikov, AA Lagunovskaya, IN Usmanova, FA Fedorenko Automation and Remote Control 77, 2018-2034, 2016 | 41 | 2016 |
Risk-averse heteroscedastic bayesian optimization A Makarova, I Usmanova, I Bogunovic, A Krause Advances in Neural Information Processing Systems 34, 17235-17245, 2021 | 34 | 2021 |
About accelerated randomized methods A Gasnikov, P Dvurechensky, I Usmanova arXiv preprint arXiv:1508.02182, 2015 | 24 | 2015 |
Fast projection onto convex smooth constraints I Usmanova, M Kamgarpour, A Krause, K Levy International Conference on Machine Learning, 10476-10486, 2021 | 15 | 2021 |
Safe non-smooth black-box optimization with application to policy search I Usmanova, A Krause, M Kamgarpour Learning for Dynamics and Control, 980-989, 2020 | 7 | 2020 |
Log barriers for safe non-convex black-box optimization I Usmanova, A Krause, M Kamgarpour arXiv preprint arXiv:1912.09478, 2019 | 5 | 2019 |
Towards Faster Global Convergence of Robust Policy Gradient Methods N Kumar, I Usmanova, KY Levy, S Mannor Sixteenth European Workshop on Reinforcement Learning, 2023 | 4 | 2023 |
Log barriers for safe black-box optimization with application to safe reinforcement learning I Usmanova, Y As, M Kamgarpour, A Krause arXiv preprint arXiv:2207.10415, 2022 | 4 | 2022 |
Safe Learning via Constrained Stochastic Optimization I Usmanova ETH Zurich, 2022 | | 2022 |
Nonlinear stochastic multiarmed bandit problems with inexact oracle A Gasnikov, E Krymova, A Lagunovskaya, I Usmanova, F Fedorenko arXiv preprint arXiv:1509.01679, 2015 | | 2015 |