DeepAI AI Chat
Log In Sign Up

On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization

by   Xingguo Li, et al.

The cyclic block coordinate descent-type (CBCD-type) methods, which performs iterative updates for a few coordinates (a block) simultaneously throughout the procedure, have shown remarkable computational performance for solving strongly convex minimization problems. Typical applications include many popular statistical machine learning methods such as elastic-net regression, ridge penalized logistic regression, and sparse additive regression. Existing optimization literature has shown that for strongly convex minimization, the CBCD-type methods attain iteration complexity of O(p(1/ϵ)), where ϵ is a pre-specified accuracy of the objective value, and p is the number of blocks. However, such iteration complexity explicitly depends on p, and therefore is at least p times worse than the complexity O((1/ϵ)) of gradient descent (GD) methods. To bridge this theoretical gap, we propose an improved convergence analysis for the CBCD-type methods. In particular, we first show that for a family of quadratic minimization problems, the iteration complexity O(^2(p)·(1/ϵ)) of the CBCD-type methods matches that of the GD methods in term of dependency on p, up to a ^2 p factor. Thus our complexity bounds are sharper than the existing bounds by at least a factor of p/^2(p). We also provide a lower bound to confirm that our improved complexity bounds are tight (up to a ^2 (p) factor), under the assumption that the largest and smallest eigenvalues of the Hessian matrix do not scale with p. Finally, we generalize our analysis to other strongly convex minimization problems beyond quadratic ones.


page 1

page 2

page 3

page 4


Randomized block proximal damped Newton method for composite self-concordant minimization

In this paper we consider the composite self-concordant (CSC) minimizati...

Iteration Complexity of Randomized Block-Coordinate Descent Methods for Minimizing a Composite Function

In this paper we develop a randomized block-coordinate descent method fo...

A Unified Convergence Analysis for Shuffling-Type Gradient Methods

In this paper, we provide a unified convergence analysis for a class of ...

Relative Interior Rule in Block-Coordinate Minimization

(Block-)coordinate minimization is an iterative optimization method whic...

Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization

Nonconvex optimization is central in solving many machine learning probl...

Block Policy Mirror Descent

In this paper, we present a new class of policy gradient (PG) methods, n...

Distributed Coordinate Descent Method for Learning with Big Data

In this paper we develop and analyze Hydra: HYbriD cooRdinAte descent me...