Skip to yearly menu bar Skip to main content

( events)   Timezone:  
Tue Dec 07 04:30 PM -- 06:00 PM (PST)
Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions
Alejandro Carderera · Mathieu Besançon · Sebastian Pokutta
Generalized self-concordance is a key property present in the objective function of many important learning problems. We establish the convergence rate of a simple Frank-Wolfe variant that uses the open-loop step size strategy $\gamma_t = 2/(t+2)$, obtaining a $\mathcal{O}(1/t)$ convergence rate for this class of functions in terms of primal gap and Frank-Wolfe gap, where $t$ is the iteration count. This avoids the use of second-order information or the need to estimate local smoothness parameters of previous work. We also show improved convergence rates for various common cases, e.g., when the feasible region under consideration is uniformly convex or polyhedral.