11 citations · 42 across the 12 of their papers we have counts for
12 papers
Safe Primal-Dual Optimization with a Single Smooth Constraint
Ilnura Usmanova, Kfir Yehuda Levy
This paper addresses the problem of safe optimization under a single smooth constraint, a scenario that arises in diverse real-world applications such as robotics and autonomous na…
Safety in the Face of Adversity: Achieving Zero Constraint Violation in Online Learning with Slowly Changing Constraints
Bassel Hamoud, Ilnura Usmanova, Kfir Y. Levy
We present the first theoretical guarantees for zero constraint violation in Online Convex Optimization (OCO) across all rounds, addressing dynamic constraint changes. Unlike exist…
Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning
Ilnura Usmanova, Yarden As, Maryam Kamgarpour +1
Optimizing noisy functions online, when evaluating the objective requires experiments on a deployed system, is a crucial task arising in manufacturing, robotics and many others. Of…
Constrained Policy Optimization via Bayesian World Models
Yarden As, Ilnura Usmanova, Sebastian Curi +1
Improving sample-efficiency and safety are crucial challenges when deploying reinforcement learning in high-stakes real world applications. We propose LAMBDA, a novel model-based a…
Risk-averse Heteroscedastic Bayesian Optimization
Anastasiia Makarova, Ilnura Usmanova, Ilija Bogunovic +1
Many black-box optimization tasks arising in high-stakes applications require risk-averse decisions. The standard Bayesian optimization (BO) paradigm, however, optimizes the expect…
Fast Projection Onto Convex Smooth Constraints
Ilnura Usmanova, Maryam Kamgarpour, Andreas Krause +1
The Euclidean projection onto a convex set is an important problem that arises in numerous constrained optimization tasks. Unfortunately, in many cases, computing projections is co…
Log Barriers for Safe Non-convex Black-box Optimization
Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour
We address the problem of minimizing a smooth function over a compact set defined by smooth functional constraints given noisy value m…
Safe non-smooth black-box optimization with application to policy search
Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour
For safety-critical black-box optimization tasks, observations of the constraints and the objective are often noisy and available only for the feasible points. We propose an approa…
Safe Convex Learning under Uncertain Constraints
Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour
We address the problem of minimizing a convex smooth function over a compact polyhedral set given a stochastic zeroth-order constraint feedback model. This problem arise…
Nonlinear stochastic multiarmed bandit problems with inexact oracle
Alexander Gasnikov, Ekaterina Krymova, Anastasia Lagunovskaya +2
In the paper we consider one point and two point multiarmed bamdit problems. In other words we consider the online stochastic convex optimization problems with oracle that return t…
About accelerated randomized methods
Alexander Gasnikov, Pavel Dvurechensky, Ilnura Usmanova
We show how one can obtain nonaccelerated randomized coordinate descent method (Yu. Nesterov, 2010) and nonaccelerated method of randomization of sum-type functional (Le Roux-Schmi…
Gradient-free prox-methods with inexact oracle for stochastic convex optimization problems on a simplex
Alexander Gasnikov, Anastasia Lagunovskaya, Ilnura Usmanova +1
In the paper we show that euclidian randomization in some situations (i.e. for gradient-free method on a simplex) can be as good as the randomization on the unit sphere in 1-norm.…