English
Related papers

Related papers: Heavy-Tail Phenomenon in Decentralized SGD

200 papers

In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers. Specifically, we firstly show that the stochastic gradient noise…

Machine Learning · Computer Science 2021-09-22 Yixin Wu , Rui Luo , Chen Zhang , Jun Wang , Yaodong Yang

Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still an important challenge. While modeling the trajectories of…

Machine Learning · Statistics 2022-01-12 Umut Şimşekli , Ozan Sener , George Deligiannidis , Murat A. Erdogdu

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Optimization and Control · Mathematics 2020-10-26 Jingzhao Zhang , Sai Praneeth Karimireddy , Andreas Veit , Seungyeon Kim , Sashank J Reddi , Sanjiv Kumar , Suvrit Sra

Despite the successes of probabilistic models based on passing noise through neural networks, recent work has identified that such methods often fail to capture tail behavior accurately, unless the tails of the base distribution are…

Machine Learning · Statistics 2023-06-16 Feynman Liang , Liam Hodgkinson , Michael W. Mahoney

We investigate high-dimensional sparse regression when both the noise and the design matrix exhibit heavy-tailed behavior. Standard algorithms typically fail in this regime, as heavy-tailed covariates distort the empirical risk geometry. We…

Methodology · Statistics 2026-01-12 Kaiyuan Zhou , Xiaoyu Zhang , Wenyang Zhang , Di Wang

In this paper, we propose a new accelerated stochastic first-order method called clipped-SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in stochastic gradients and derive the first high-probability…

Optimization and Control · Mathematics 2020-10-26 Eduard Gorbunov , Marina Danilova , Alexander Gasnikov

While implicit regularization facilitates benign overfitting in low-noise regimes, recent theoretical work predicts a sharp phase transition to harmful overfitting as the noise-to-signal ratio increases. We experimentally isolate the…

Machine Learning · Computer Science 2026-04-07 Zice Wang

We introduce a general framework for nonlinear stochastic gradient descent (SGD) for the scenarios when gradient noise exhibits heavy tails. The proposed framework subsumes several popular nonlinearity choices, like clipped, normalized,…

Optimization and Control · Mathematics 2022-04-07 Dusan Jakovetic , Dragana Bajovic , Anit Kumar Sahu , Soummya Kar , Nemanja Milosevic , Dusan Stamenkovic

Stochastic gradient descent with momentum (SGDm) is one of the most popular optimization algorithms in deep learning. While there is a rich theory of SGDm for convex problems, the theory is considerably less developed in the context of deep…

Machine Learning · Statistics 2020-11-05 Umut Şimşekli , Lingjiong Zhu , Yee Whye Teh , Mert Gürbüzbalaban

Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order methods can significantly accelerate convergence in…

Optimization and Control · Mathematics 2025-10-14 Abdurakhmon Sadiev , Peter Richtárik , Ilyas Fatkhullin

Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- common in modern machine learning and reinforcement learning -- remains poorly understood. In this…

Optimization and Control · Mathematics 2025-08-08 Ilyas Fatkhullin , Florian Hübler , Guanghui Lan

We study high-probability convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. In the proposed scenario, the model is updated in an online fashion, as new information is observed, without storing any…

Machine Learning · Computer Science 2024-05-02 Aleksandar Armacki , Pranay Sharma , Gauri Joshi , Dragana Bajovic , Dusan Jakovetic , Soummya Kar

This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise. To deal with heavy-tailed noise whose variance can be infinite, we adopt the quantile regression loss…

Methodology · Statistics 2020-09-21 Xi Chen , Weidong Liu , Xiaojun Mao , Zhuoyi Yang

Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is…

Machine Learning · Computer Science 2026-05-14 Hamza Cherkaoui , Hélène Halconruy , Antonio Ocello

Constructions of numerous approximate sampling algorithms are based on the well-known fact that certain Gibbs measures are stationary distributions of ergodic stochastic differential equations (SDEs) driven by the Brownian motion. However,…

Probability · Mathematics 2020-07-07 Lu-Jing Huang , Mateusz B. Majka , Jian Wang

Despite the ubiquitous use of stochastic optimization algorithms in machine learning, the precise impact of these algorithms and their dynamics on generalization performance in realistic non-convex settings is still poorly understood. While…

Machine Learning · Statistics 2022-07-12 Liam Hodgkinson , Umut Şimşekli , Rajiv Khanna , Michael W. Mahoney

We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting…

Machine Learning · Computer Science 2024-08-20 Puning Zhao , Jiafei Wu , Zhe Liu , Chong Wang , Rongfei Fan , Qingming Li

Stochastic gradients closely relate to both optimization and generalization of deep neural networks (DNNs). Some works attempted to explain the success of stochastic optimization for deep learning by the arguably heavy-tail properties of…

Machine Learning · Computer Science 2023-10-23 Zeke Xie , Qian-Yuan Tang , Mingming Sun , Ping Li

We characterise the learning of a mixture of two clouds of data points with generic centroids via empirical risk minimisation in the high dimensional regime, under the assumptions of generic convex loss and convex regularisation. Each cloud…

Machine Learning · Statistics 2024-03-19 Urte Adomaityte , Gabriele Sicuro , Pierpaolo Vivo

Recent empirical evidence indicates that many machine learning applications involve heavy-tailed gradient noise, which challenges the standard assumptions of bounded variance in stochastic optimization. Gradient clipping has emerged as a…

Optimization and Control · Mathematics 2025-07-10 Florian Hübler , Ilyas Fatkhullin , Niao He