paper-with-me

Papers

SEGA: Variance Reduction via Gradient Sketching

2018-09-09 · NeurIPS 2018 12 · Filip Hanzely, Konstantin Mishchenko, Peter Richtarik

We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the gradient from random linear measurements (sketches) of the gradient obtained from an oracle. In each iteration, SEGA updates the current estimate of the gradient through a sketch-and-project operation using the information provided by the latest sketch, and this is subsequently used to compute an unbiased estimate of the true gradient through a random relaxation procedure. This unbiased estimate is then used to perform a gradient step. Unlike standard subspace descent methods, such as coordinate descent, SEGA can be used for optimization problems with a non-separable proximal term. We provide a general convergence analysis and prove linear convergence for strongly convex objectives. In the special case of coordinate sketches, SEGA can be enhanced with various techniques such as importance sampling, minibatching and acceleration, and its rate is up to a small constant factor identical to the best-known rate of coordinate descent.

📄 PDF Abstract BibTeX arXiv:1809.03054

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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 speci…

All

VISReg: Variance-Invariance-Sketching Regularization for JEPA training

2026-06-01 · Haiyu Wu, Randall Balestriero, Morgan Levine arxiv

Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regularization into variance and covariance objec…

Self-Supervised Learning

Sequential Low-Rank Change Detection

2016-10-03 · Yao Xie, Lee Seversky

Detecting emergence of a low-rank signal from high-dimensional data is an important problem arising from many applications such as camera surveillance and swarm monitoring using sensors. We consider a procedure based on …

Change DetectionDimensionality Reduction

An Investigation of Newton-Sketch and Subsampled Newton Methods

2017-05-17 · Albert S. Berahas, Raghu Bollapragada, Jorge Nocedal

Sketching, a dimensionality reduction technique, has received much attention in the statistics community. In this paper, we study sketching in the context of Newton's method for solving finite-sum optimization problems i…

Dimensionality Reduction

New Bounds for the Last Iterate of the Stochastic subGradient Method

2026-06-23 · Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni, Andrea Paudice arxiv

We study the last iterate of the stochastic subgradient method for one-dimensional convex Lipschitz objectives. For a fixed horizon $n$, we consider the standard fixed stepsizes $η=Θ(1/\sqrt n)$. We prove that, for such …