Timezone: »

Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
Xufeng Cai · Chaobing Song · Stephen Wright · Jelena Diakonikolas

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #132

Nonconvex optimization is central in solving many machine learning problems, in which block-wise structure is commonly encountered. In this work, we propose cyclic block coordinate methods for nonconvex optimization problems with non-asymptotic gradient norm guarantees. Our convergence analysis is based on a gradient Lipschitz condition with respect to a Mahalanobis norm, inspired by a recent progress on cyclic block coordinate methods. In deterministic settings, our convergence guarantee matches the guarantee of (full-gradient) gradient descent, but with the gradient Lipschitz constant being defined w.r.t. a Mahalanobis norm. In stochastic settings, we use recursive variance reduction to decrease the per-iteration cost and match the arithmetic operation complexity of current optimal stochastic full-gradient methods, with a unified analysis for both finite-sum and infinite-sum cases. We prove a faster linear convergence result when a Polyak-Łojasiewicz (PŁ) condition holds. To our knowledge, this work is the first to provide non-asymptotic convergence guarantees --- variance-reduced or not --- for a cyclic block coordinate method in general composite (smooth + nonsmooth) nonconvex settings. Our experimental results demonstrate the efficacy of the proposed cyclic scheme in training deep neural nets.

Author Information

Xufeng Cai (UW-Madison)
Chaobing Song (University of Wisconsin-Madison)
Stephen Wright (University of Wisconsin-Madison)
Jelena Diakonikolas (University of Wisconsin-Madison)

More from the Same Authors