Abstract: We consider structured online convex optimization (OCO) with bandit feedback, where either the loss function is smooth or the constraint set is strongly convex. Projection-free methods are ...

Given any algorithm for convex optimization that uses exact first-order information (i.e., function values and subgradients), we show how to use such an algorithm to solve the problem with access to ...

Convex geometry and combinatorial optimisation form a vibrant nexus of research that bridges theoretical mathematics with practical algorithm design. The study of convex sets and their structural ...

ABSTRACT: In this paper we consider three problems in continuous multi-criteria optimization: An application of the Berge Maximum Theorem, properties of Pareto-retract mappings, and the structure of ...