181 citations · 620 across the 171 of their papers we have counts for
7 papers · 2 filters
Flexible block-iterative analysis for the Frank-Wolfe algorithm
Gábor Braun, Jannis Halbey, Sebastian Pokutta +1
We prove that the block-coordinate Frank-Wolfe (BCFW) algorithm converges with state-of-the-art rates in both convex and nonconvex settings under a very mild "block-iterative" assu…
Better bounds on finite-order Grothendieck constants
Sébastien Designolle, Tamás Vértesi, Sebastian Pokutta
Grothendieck constants bound the advantage of -dimensional strategies over -dimensional ones in a specific optimisation task. They have applications ranging from app…
The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control
Elias Wirth, Mathieu Besançon, Sebastian Pokutta
We propose the pivoting meta algorithm (PM) to enhance optimization algorithms that generate iterates as convex combinations of vertices of a feasible region $C\subseteq \mathbb{R}…
Fast convergence of Frank-Wolfe algorithms on polytopes
Elias Wirth, Javier Pena, Sebastian Pokutta
We provide a template to derive convergence rates for the following popular versions of the Frank-Wolfe algorithm on polytopes: vanilla Frank-Wolfe, Frank-Wolfe with away steps, Fr…
Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
David Martínez-Rubio, Christophe Roux, Sebastian Pokutta
In this work, we analyze two of the most fundamental algorithms in geodesically convex optimization: Riemannian gradient descent and (possibly inexact) Riemannian proximal point. W…
Norm-induced Cuts: Outer Approximation for Lipschitzian Constraint Functions
Adrian Göß, Alexander Martin, Sebastian Pokutta +1
In this paper, we consider a finite-dimensional optimization problem minimizing a continuous objective on a compact domain subject to a multi-dimensional constraint function. For t…
Network Design for the Traffic Assignment Problem with Mixed-Integer Frank-Wolfe
Kartikey Sharma, Deborah Hendrych, Mathieu Besançon +1
We tackle the network design problem for centralized traffic assignment, which can be cast as a mixed-integer convex optimization (MICO) problem. For this task, we propose differen…