paper-with-me

홈 › Papers

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling

2015-12-30 · Zeyuan Allen-Zhu, Zheng Qu, Peter Richtárik, Yang Yuan

Accelerated coordinate descent is widely used in optimization due to its cheap per-iteration cost and scalability to large-scale problems. Up to a primal-dual transformation, it is also the same as accelerated stochastic gradient descent that is one of the central methods used in machine learning. In this paper, we improve the best known running time of accelerated coordinate descent by a factor up to $\sqrt{n}$. Our improvement is based on a clean, novel non-uniform sampling that selects each coordinate with a probability proportional to the square root of its smoothness parameter. Our proof technique also deviates from the classical estimation sequence technique used in prior work. Our speed-up applies to important problems such as empirical risk minimization and solving linear systems, both in theory and in practice.

📄 PDF Abstract BibTeX arXiv:1512.09103

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A2BCD: Asynchronous Acceleration with Optimal Complexity

2019-05-01 · ICLR 2019 5 · Robert Hannah, Fei Feng, Wotao Yin

In this paper, we propose the Asynchronous Accelerated Nonuniform Randomized Block Coordinate Descent algorithm (A2BCD). We prove A2BCD converges linearly to a solution of the convex minimization problem at the same rat…

Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning

2019-05-23 · Shuai Zheng, James T. Kwok

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradi…

Deep Learning

Approximate Steepest Coordinate Descent

2017-06-26 · ICML 2017 8 · Sebastian U. Stich, Anant Raj, Martin Jaggi

We propose a new selection rule for the coordinate selection in coordinate descent methods for huge-scale optimization. The efficiency of this novel scheme is provably better than the efficiency of uniformly random selec…

Computational Efficiencyregression

Anderson acceleration of coordinate descent

2020-11-19 · Quentin Bertrand, Mathurin Massias

Acceleration of first order methods is mainly obtained via inertial techniques \`a la Nesterov, or via nonlinear extrapolation. The latter has known a recent surge of interest, with successful applications to gradient an…

regression

Accelerating Greedy Coordinate Descent Methods

2018-07-01 · ICML 2018 7 · Haihao Lu, Robert Freund, Vahab Mirrokni

We introduce and study two algorithms to accelerate greedy coordinate descent in theory and in practice: Accelerated Semi-Greedy Coordinate Descent (ASCD) and Accelerated Greedy Coordinate Descent (AGCD). On the the…