Mar 11, 2019 · This problem arises in safety-critical machine learning applications, such as personalized medicine and robotics.
Our objective is to design an algorithm that sequentially steers the decisions towards the optimum while ensur- ing safety of the decisions at every step. In ...
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 ...
In each iter- ation, it solves an uncertain linear program based on estimates of the constraints and uses this solution to define the step direction. The safety ...
This problem arises in safety-critical machine learning applications, such as personalized medicine and robotics. In such cases, one needs to ensure constraints ...
This work proposes a new variant of the Frank-Wolfe algorithm, which provides the convergence rate of the algorithm while guaranteeing feasibility of all ...
In this paper, we consider non-convex optimization problems under\textit {unknown} yet safety-critical constraints.
Jun 23, 2020 · Abstract. In this paper, we consider non-convex optimization problems under unknown yet safety- critical constraints.
An algorithm called Reliable Frank-Wolfe (Reliable-FW) is developed that simultaneously learns the landscape of the objective function and the boundary of ...
Jun 28, 2022 · We study the problem of safe online convex optimization, where the action at each time step must satisfy a set of linear safety constraints.
Missing: Uncertain | Show results with:Uncertain