To deal with non-stationary online problems with complex constraints, we investigate the
dynamic regret of online Frank-Wolfe (OFW), which is an efficient projection-free algorithm …

This paper presents new projection-free algorithms for Online Convex Optimization (OCO)
over a convex domain $\mathcal {K}\subset\mathbb {R}^ d $. Classical OCO algorithms …

The projection operation is a critical component in a wide range of optimization algorithms,
such as online gradient descent (OGD), for enforcing constraints and achieving optimal …

Projection-free online learning, which eschews the projection operation via less expensive
computations such as linear optimization (LO), has received much interest recently due to its …

In this paper, we explore online convex optimization (OCO) and introduce a new analysis
that provides fast rates by exploiting the curvature of feasible sets. In online linear …

This paper presents new projection-free algorithms for Online Convex Optimization (OCO)
over a convex domain K⊂ ℝ d. Classical OCO algorithms (such as Online Gradient …

Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
` `%%%`#`&12_`__~~~ౡ Page 1 1 / 15 Fast Rates in Stochastic Online Convex Optimization …