paper-with-me

홈 › Papers

Dual Free Adaptive Mini-batch SDCA for Empirical Risk Minimization

2015-10-22 · Xi He, Martin Takáč

In this paper we develop dual free mini-batch SDCA with adaptive probabilities for regularized empirical risk minimization. This work is motivated by recent work of Shai Shalev-Shwartz on dual free SDCA method, however, we allow a non-uniform selection of "dual" coordinates in SDCA. Moreover, the probability can change over time, making it more efficient than fix uniform or non-uniform selection. We also propose an efficient procedure to generate a random non-uniform mini-batch through iterative process. The work is concluded with multiple numerical experiments to show the efficiency of proposed algorithms.

📄 PDF Abstract BibTeX arXiv:1510.06684

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accelerated Mini-Batch Stochastic Dual Coordinate Ascent

2013-05-12 · NeurIPS 2013 12 · Shai Shalev-Shwartz, Tong Zhang

Stochastic dual coordinate ascent (SDCA) is an effective technique for solving regularized loss minimization problems in machine learning. This paper considers an extension of SDCA under the mini-batch setting that is of…

BIG-bench Machine Learning

Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses

2015-06-07 · Dominik Csiba, Peter Richtárik

In this work we develop a new algorithm for regularized empirical risk minimization. Our method extends recent techniques of Shalev-Shwartz [02/2015], which enable a dual-free analysis of SDCA, to arbitrary mini-batching…

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

2015-02-27 · Dominik Csiba, Zheng Qu, Peter Richtárik

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method adaptively…

Distributed Mini-Batch SDCA

2015-07-29 · Martin Takáč, Peter Richtárik, Nathan Srebro

We present an improved analysis of mini-batched stochastic dual coordinate ascent for regularized empirical loss minimization (i.e. SVM and SVM-type objectives). Our analysis allows for flexible sampling schemes, includi…

Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization

2021-09-29 · ICLR 2022 4 · Kazusato Oko, Taiji Suzuki, Atsushi Nitanda, Denny Wu

We introduce Particle-SDCA, a gradient-based optimization algorithm for two-layer neural networks in the mean field regime that achieves exponential convergence rate in regularized empirical risk minimization. The propos…