Sharpness-aware minimization (SAM) has well documented merits in enhancing
generalization of deep neural networks, even without sizable data augmentation. Embracing …

This paper considers distributed stochastic optimization, in which a number of agents
cooperate to optimize a global objective function through local computations and information …

Collision detection between two convex shapes is an essential feature of any physics
engine or robot motion planner. It has often been tackled as a computational geometry …

Recent papers have shown that the Frank–Wolfe algorithm (FW) with open-loop step-sizes
exhibits rates of convergence faster than the iconic O (t-1) rate. In particular, when the …

Distribution shift is a key challenge for predictive models in practice, creating the need to
identify potentially harmful shifts in advance of deployment. Existing work typically defines …

Abstract Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented
merits in machine learning and signal processing applications. Unlike projection-based …

Frank-Wolfe algorithms (FW) are popular first-order methods for solving constrained convex
optimization problems that rely on a linear minimization oracle instead of potentially …

In this study, we deal with the problem of scheduling charging periods of electrical vehicles
(EVs) to satisfy the users' demands for energy consumption as well as to optimally utilize the …

This paper considers stochastic convex optimization problems with two sets of
constraints:(a) deterministic constraints on the domain of the optimization variable, which are …

Abstract The Frank-Wolfe algorithm is a popular method in structurally constrained machine
learning applications, due to its fast per-iteration complexity. However, one major limitation …