paper-with-me

Papers

Optimal Stochastic and Online Learning with Individual Iterates

2019-12-01 · NeurIPS 2019 12 · Yunwen Lei, Peng Yang, Ke Tang, Ding-Xuan Zhou

Stochastic composite mirror descent (SCMD) is a simple and efficient method able to capture both geometric and composite structures of optimization problems in machine learning. Existing strategies require to take either an average or a random selection of iterates to achieve optimal convergence rates, which, however, can either destroy the sparsity of solutions or slow down the practical training speed. In this paper, we propose a theoretically sound strategy to select an individual iterate of the vanilla SCMD, which is able to achieve optimal rates for both convex and strongly convex problems in a non-smooth learning setting. This strategy of outputting an individual iterate can preserve the sparsity of solutions which is crucial for a proper interpretation in sparse learning problems. We report experimental comparisons with several baseline methods to show the effectiveness of our method in achieving a fast training speed as well as in outputting sparse solutions.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Sparse Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Anytime Online-to-Batch Conversions, Optimism, and Acceleration

2019-03-03 · Ashok Cutkosky

A standard way to obtain convergence guarantees in stochastic convex optimization is to run an online learning algorithm and then output the average of its iterates: the actual iterates of the online learning algorithm d…

Nonlinear Acceleration of Stochastic Algorithms

2017-12-01 · NeurIPS 2017 12 · Damien Scieur, Francis Bach, Alexandre d'Aspremont

Extrapolation methods use the last few iterates of an optimization algorithm to produce a better estimate of the optimum. They were shown to achieve optimal convergence rates in a deterministic setting using simple gradi…

A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging

2025-05-27 · Sajad Khodadadian, Martin Zubeldia

Polyak-Ruppert averaging is a widely used technique to achieve the optimal asymptotic variance of stochastic approximation (SA) algorithms, yet its high-probability performance guarantees remain underexplored in general …

Q-Learning

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent

2025-02-10 · Marina Sheshukova, Sergey Samsonov, Denis Belomestny, Eric Moulines 외

In this paper, we establish non-asymptotic convergence rates in the central limit theorem for Polyak-Ruppert-averaged iterates of stochastic gradient descent (SGD). Our analysis builds on the result of the Gaussian appro…

Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models

2024-09-11 · Jiaqi Li, Johannes Schmidt-Hieber, Wei Biao Wu

This paper proposes an asymptotic theory for online inference of the stochastic gradient descent (SGD) iterates with dropout regularization in linear regression. Specifically, we establish the geometric-moment contractio…