Timezone: »

A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming
Alp Yurtsever · Olivier Fercoq · Francesco Locatello · Volkan Cevher

Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ A9

We propose a conditional gradient framework for a composite convex minimization template with broad applications. Our approach combines smoothing and homotopy techniques under the CGM framework, and provably achieves the optimal convergence rate. We demonstrate that the same rate holds if the linear subproblems are solved approximately with additive or multiplicative error. In contrast with the relevant work, we are able to characterize the convergence when the non-smooth term is an indicator function. Specific applications of our framework include the non-smooth minimization, semidefinite programming, and minimization with linear inclusion constraints over a compact domain. Numerical evidence demonstrates the benefits of our framework.

Author Information

Alp Yurtsever (EPFL)
Olivier Fercoq (Télécom Paris, IP Paris)
Francesco Locatello (ETH Zurich - Max Planck Institute)
Volkan Cevher (EPFL)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors