paper-with-me

Papers

SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance

2023-02-17 · Amit Attia, Tomer Koren

We study Stochastic Gradient Descent with AdaGrad stepsizes: a popular adaptive (self-tuning) method for first-order stochastic optimization. Despite being well studied, existing analyses of this method suffer from various shortcomings: they either assume some knowledge of the problem parameters, impose strong global Lipschitz conditions, or fail to give bounds that hold with high probability. We provide a comprehensive analysis of this basic method without any of these limitations, in both the convex and non-convex (smooth) cases, that additionally supports a general ``affine variance'' noise model and provides sharp rates of convergence in both the low-noise and high-noise~regimes.

📄 PDF Abstract BibTeX arXiv:2302.08783

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Methods 이 논문이 사용한 방법론

fail 설명 없음
AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…

Similar Papers 제목 키워드 기반

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

2024-06-06 · Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov 외

Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the stochastic gradients is heavy-tailed for th…

Stochastic Optimization

On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes

2018-05-21 · Xiaoyu Li, Francesco Orabona

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This …

AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates

2025-09-03 · Minxin Zhang, Yuxuan Liu, Hayden Schaeffer arxiv

The recently proposed Muon optimizer updates weight matrices via orthogonalized momentum and has demonstrated strong empirical success in large language model training. However, it remains unclear how to determine the le…

AdaGrad stepsizes: Sharp convergence over nonconvex landscapes

2018-06-05 · Rachel Ward, Xiaoxia Wu, Leon Bottou

Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large…

Stochastic Optimization

Private Adaptive Gradient Methods for Convex Optimization

2021-06-25 · Hilal Asi, John Duchi, Alireza Fallah, Omid Javidbakht 외

We study adaptive methods for differentially private convex optimization, proposing and analyzing differentially private variants of a Stochastic Gradient Descent (SGD) algorithm with adaptive stepsizes, as well as the A…