paper-with-me

홈 › Papers

When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent

2017-12-01 · NeurIPS 2017 12 · Mert Gurbuzbalaban, Asuman Ozdaglar, Pablo A. Parrilo, Nuri Vanli

The coordinate descent (CD) method is a classical optimization algorithm that has seen a revival of interest because of its competitive performance in machine learning applications. A number of recent papers provided convergence rate estimates for their deterministic (cyclic) and randomized variants that differ in the selection of update coordinates. These estimates suggest randomized coordinate descent (RCD) performs better than cyclic coordinate descent (CCD), although numerical experiments do not provide clear justification for this comparison. In this paper, we provide examples and more generally problem classes for which CCD (or CD with any deterministic order) is faster than RCD in terms of asymptotic worst-case convergence. Furthermore, we provide lower and upper bounds on the amount of improvement on the rate of CCD relative to RCD, which depends on the deterministic order used. We also provide a characterization of the best deterministic order (that leads to the maximum improvement in convergence rate) in terms of the combinatorial properties of the Hessian matrix of the objective function.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Importance sampling strategy for non-convex randomized block-coordinate descent

2016-06-23 · Rémi Flamary, Alain Rakotomamonjy, Gilles Gasso

As the number of samples and dimensionality of optimization problems related to statistics an machine learning explode, block coordinate descent algorithms have gained popularity since they reduce the original problem to…

Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization

2026-05-14 · Chen Liang, Xiatao Sun, Qian Wang, Daniel Rakita arxiv

Zeroth-Order (ZO) optimization is pivotal for scenarios where backpropagation is unavailable, such as memory-constrained on-device learning and black-box optimization. However, existing methods face a stark trade-off: th…

Understanding Limitation of Two Symmetrized Orders by Worst-case Complexity

2019-10-10 · Peijun Xiao, Zhisheng Xiao, Ruoyu Sun

Update order is one of the major design choices of block decomposition algorithms. There are at least two classes of deterministic update orders: nonsymmetric (e.g. cyclic order) and symmetric (e.g. Gaussian back substit…

Vocal Bursts Valence Prediction

Accelerated Randomized Coordinate Descent Algorithms for Stochastic Optimization and Online Learning

2018-06-05 · Akshita Bhandari, Chandramani Singh

We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorit…

Stochastic Optimization

Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks

2017-11-20 · Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong

We present a stochastic first-order optimization algorithm, named BCSC, that adds a cyclic constraint to stochastic block-coordinate descent. It uses different subsets of the data to update different subsets of the param…