paper-with-me

Papers

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

2019-05-27 · Filip Hanzely, Peter Richtárik

We propose a remarkably general variance-reduced method suitable for solving regularized empirical risk minimization problems with either a large number of training examples, or a large model dimension, or both. In special cases, our method reduces to several known and previously thought to be unrelated methods, such as {\tt SAGA}, {\tt LSVRG}, {\tt JacSketch}, {\tt SEGA} and {\tt ISEGA}, and their arbitrary sampling and proximal generalizations. However, we also highlight a large number of new specific algorithms with interesting properties. We provide a single theorem establishing linear convergence of the method under smoothness and quasi strong convexity assumptions. With this theorem we recover best-known and sometimes improved rates for known methods arising in special cases. As a by-product, we provide the first unified method and theory for stochastic gradient and stochastic coordinate descent type methods.

📄 PDF Abstract BibTeX arXiv:1905.11266

Code (0)

등록된 구현이 없습니다.

Tasks

All

Similar Papers 제목 키워드 기반

A PAC-Bayesian Tutorial with A Dropout Bound

2013-07-08 · David McAllester

This tutorial gives a concise overview of existing PAC-Bayesian theory focusing on three generalization bounds. The first is an Occam bound which handles rules with finite precision parameters and which states that gener…

Generalization Bounds

Portfolio Optimization Rules beyond the Mean-Variance Approach

2023-05-15 · Maxime Markov, Vladimir Markov

In this paper, we revisit the relationship between investors' utility functions and portfolio allocation rules. We derive portfolio allocation rules for asymmetric Laplace distributed $ALD(\mu,\sigma,\kappa)$ returns and…

Portfolio Optimization

A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks

2015-11-30 · NeurIPS 2015 12 · Cengiz Pehlevan, Dmitri B. Chklovskii

To make sense of the world our brains must analyze high-dimensional datasets streamed by our sensory organs. Because such analysis begins with dimensionality reduction, modelling early sensory processing requires biologi…

Dimensionality Reduction

GO Gradient for Expectation-Based Objectives

2019-01-17 · ICLR 2019 5 · Yulai Cong, Miaoyun Zhao, Ke Bai, Lawrence Carin

Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$. Most ex…

Stochastic variance reduced multiplicative update for nonnegative matrix factorization

2017-10-30 · Hiroyuki Kasai

Nonnegative matrix factorization (NMF), a dimensionality reduction and factor analysis method, is a special case in which factor matrices have low-rank nonnegative constraints. Considering the stochastic learning in NMF,…

Dimensionality Reduction