Timezone: »

Semi-Proximal Mirror-Prox for Nonsmooth Composite Minimization
Niao He · Zaid Harchaoui

Tue Dec 08 04:00 PM -- 08:59 PM (PST) @ 210 C #87

We propose a new first-order optimization algorithm to solve high-dimensional non-smooth composite minimization problems. Typical examples of such problems have an objective that decomposes into a non-smooth empirical risk part and a non-smooth regularization penalty. The proposed algorithm, called Semi-Proximal Mirror-Prox, leverages the saddle point representation of one part of the objective while handling the other part of the objective via linear minimization over the domain. The algorithm stands in contrast with more classical proximal gradient algorithms with smoothing, which require the computation of proximal operators at each iteration and can therefore be impractical for high-dimensional problems. We establish the theoretical convergence rate of Semi-Proximal Mirror-Prox, which exhibits the optimal complexity bounds for the number of calls to linear minimization oracle. We present promising experimental results showing the interest of the approach in comparison to competing methods.

Author Information

Niao He (Georgia Institute of Technology)
Zaid Harchaoui (Inria)

More from the Same Authors