paper-with-me

홈 › Papers

Fast Distributed Coordinate Descent for Non-Strongly Convex Losses

2014-05-21 · Olivier Fercoq, Zheng Qu, Peter Richtárik, Martin Takáč

We propose an efficient distributed randomized coordinate descent method for minimizing regularized non-strongly convex loss functions. The method attains the optimal $O(1/k^2)$ convergence rate, where $k$ is the iteration counter. The core of the work is the theoretical study of stepsize parameters. We have implemented the method on Archer - the largest supercomputer in the UK - and show that the method is capable of solving a (synthetic) LASSO optimization problem with 50 billion variables.

📄 PDF Abstract BibTeX arXiv:1405.5300

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Markov Chain Block Coordinate Descent

2018-11-22 · Tao Sun, Yuejiao Sun, Yangyang Xu, Wotao Yin

The method of block coordinate gradient descent (BCD) has been a powerful method for large-scale optimization. This paper considers the BCD method that successively updates a series of blocks selected according to a Mark…

Distributed Optimization

On Centralized and Distributed Mirror Descent: Convergence Analysis Using Quadratic Constraints

2021-05-29 · Youbang Sun, Mahyar Fazlyab, Shahin Shahrampour

Mirror descent (MD) is a powerful first-order optimization technique that subsumes several optimization algorithms including gradient descent (GD). In this work, we develop a semi-definite programming (SDP) framework to …

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

2016-07-10 · Xingguo Li, Tuo Zhao, Raman Arora, Han Liu 외

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 …

regression

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates

2018-03-05 · ICML 2018 7 · Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbi…

Random extrapolation for primal-dual coordinate descent

2020-07-13 · ICML 2020 1 · Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher

We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function. Our method updates only a subset of primal and…