OCLGDec 9, 2022

Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization

arXiv:2212.05088v229 citationsh-index: 64
AI Analysis

This addresses optimization efficiency for machine learning problems with block-wise structure, offering incremental improvements in convergence analysis and computational cost.

The paper tackles nonconvex optimization with block-wise structure by proposing cyclic block coordinate methods with variance reduction, achieving non-asymptotic gradient norm guarantees and matching the complexity of optimal stochastic full-gradient methods, with experimental validation on deep neural nets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes