1 code implementation • 24 Oct 2015 • Emanuele Frandi, Ricardo Nanculef, Stefano Lodi, Claudio Sartori, Johan A. K. Suykens
Frank-Wolfe (FW) algorithms have been often proposed over the last few years as efficient solvers for a variety of optimization problems arising in the field of Machine Learning.
no code implementations • 5 Feb 2015 • Emanuele Frandi, Ricardo Nanculef, Johan A. K. Suykens
Frank-Wolfe algorithms have recently regained the attention of the Machine Learning community.
no code implementations • 15 Oct 2014 • Emanuele Frandi, Ricardo Nanculef, Johan Suykens
Frank-Wolfe algorithms for convex minimization have recently gained considerable attention from the Optimization and Machine Learning communities, as their properties make them a suitable choice in a variety of applications.
no code implementations • 3 Apr 2013 • Hector Allende, Emanuele Frandi, Ricardo Nanculef, Claudio Sartori
In this paper, we present and analyze a novel variant of the FW method based on a new way to perform away steps, a classic strategy used to accelerate the convergence of the basic FW procedure.