paper-with-me

Papers

Accelerated Gradient Flow: Risk, Stability, and Implicit Regularization

2022-01-20 · Yue Sheng, Alnur Ali

Acceleration and momentum are the de facto standard in modern applications of machine learning and optimization, yet the bulk of the work on implicit regularization focuses instead on unaccelerated methods. In this paper, we study the statistical risk of the iterates generated by Nesterov's accelerated gradient method and Polyak's heavy ball method, when applied to least squares regression, drawing several connections to explicit penalization. We carry out our analyses in continuous-time, allowing us to make sharper statements than in prior work, and revealing complex interactions between early stopping, stability, and the curvature of the loss function.

📄 PDF Abstract BibTeX arXiv:2201.08311

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer

2022-09-29 · Valentin Leplat, Daniil Merkulov, Aleksandr Katrutsa, Daniel Bershatsky 외

Classical machine learning models such as deep neural networks are usually trained by using Stochastic Gradient Descent-based (SGD) algorithms. The classical SGD can be interpreted as a discretization of the stochastic g…

SHANG++: Robust Stochastic Acceleration under Multiplicative Noise

2026-03-10 · Yaxin Yu, Long Chen, Minfu Feng arxiv

Under the multiplicative noise scaling (MNS) condition, original Nesterov acceleration is provably sensitive to noise and may diverge when gradient noise overwhelms the signal. In this paper, we develop two accelerated s…

Accelerated Gradient Methods for Stochastic Optimization and Online Learning

2009-12-01 · NeurIPS 2009 12 · Chonghai Hu, Weike Pan, James T. Kwok

Regularized risk minimization often involves non-smooth optimization, either because of the loss function (e.g., hinge loss) or the regularizer (e.g., $\ell_1$-regularizer). Gradient descent methods, though highly scalab…

Stochastic Optimization

Algorithmic Instabilities of Accelerated Gradient Descent

2021-02-03 · NeurIPS 2021 12 · Amit Attia, Tomer Koren

We study the algorithmic stability of Nesterov's accelerated gradient method. For convex quadratic objectives, Chen et al. (2018) proved that the uniform stability of the method grows quadratically with the number of opt…

Accelerating Stochastic Gradient Descent For Least Squares Regression

2017-04-26 · Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli 외

There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their i…

regressionStochastic Optimization