paper-with-me

Papers

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

2024-06-06 · Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander Gasnikov, Samuel Horváth, Martin Takáč, Eduard Gorbunov

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 the later ones. Gradient clipping provably helps to achieve good high-probability convergence for such noises. However, despite the similarity between AdaGrad/Adam and Clip-SGD, the current understanding of the high-probability convergence of AdaGrad/Adam-type methods is limited in this case. In this work, we prove that AdaGrad/Adam (and their delayed version) can have provably bad high-probability convergence if the noise is heavy-tailed. We also show that gradient clipping fixes this issue, i.e., we derive new high-probability convergence bounds with polylogarithmic dependence on the confidence level for AdaGrad-Norm and Adam-Norm with clipping and with/without delay for smooth convex/non-convex stochastic optimization with heavy-tailed noise. Our empirical evaluations highlight the superiority of clipped versions of AdaGrad/Adam-Norm in handling the heavy-tailed noise.

📄 PDF Abstract BibTeX arXiv:2406.04443

Code (1)

yaroslavkliukin/Clipped-AdaGrad-and-Adam 공식 구현 pytorch

Tasks

Stochastic Optimization

Methods 이 논문이 사용한 방법론

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…
Gradient Clipping One difficulty that arises with optimization of deep neural networks is that large parameter gradients can lead an SGD optimizer to update…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad

2026-05-18 · Zijian Liu arxiv

Many tasks in modern machine learning are observed to involve heavy-tailed gradient noise during the optimization process. To manage this realistic and challenging setting, new mechanisms, such as gradient clipping and g…

Enhancing LLM Training via Spectral Clipping

2026-03-15 · Xiaowen Jiang, Andrei Semenov, Sebastian U. Stich arxiv

While spectral-based optimizers like Muon operate directly on the spectrum of updates, standard adaptive methods such as AdamW do not account for the spectral structure of weights and gradients, leaving them vulnerable t…

A Simple Convergence Proof of Adam and Adagrad

2020-03-05 · Alexandre Défossez, Léon Bottou, Francis Bach, Nicolas Usunier

We provide a simple proof of convergence covering both the Adam and Adagrad adaptive optimization algorithms when applied to smooth (possibly non-convex) objective functions with bounded gradients. We show that in expect…

Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees

2024-11-11 · Thien Hang Nguyen, Huy Le Nguyen

We introduce two complementary techniques for efficient optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique, Subset-Norm step size, generalizes Ada…

Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam

2025-02-24 · Tianjin Huang, Haotian Hu, Zhenyu Zhang, Gaojie Jin 외

This paper comprehensively evaluates several recently proposed optimizers for 4-bit training, revealing that low-bit precision amplifies sensitivity to learning rates and often causes unstable gradient norms, leading to …