English
Related papers

Related papers: Heavy-Tail Phenomenon in Decentralized SGD

200 papers

The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly determined by the average loss assessed on a testing set,…

Machine Learning · Computer Science 2023-06-06 Etrit Haxholli , Marco Lorenzi

Understanding the behavior of stochastic gradient methods is a central problem in modern machine learning. Recent work has highlighted diagonal linear networks as a simplified yet expressive setting for analyzing the optimization and…

Optimization and Control · Mathematics 2026-05-19 Begoña García Malaxechebarría , Courtney Paquette , Maryam Fazel , Dmitriy Drusvyatskiy

Extreme events and the heavy tail distributions driven by them are ubiquitous in various scientific, engineering and financial research. They are typically associated with stochastic instability caused by hidden unresolved processes.…

Probability · Mathematics 2019-05-22 Andrew J. Majda , Xin T. Tong

Distributed methods are essential for handling machine learning pipelines comprising large-scale models and datasets. However, their benefits often come at the cost of increased communication overhead between the central server and agents,…

Machine Learning · Computer Science 2025-03-03 Enea Monzio Compagnoni , Rustem Islamov , Frank Norbert Proske , Aurelien Lucchi

Learning the tail behavior of a distribution is a notoriously difficult problem. By definition, the number of samples from the tail is small, and deep generative models, such as normalizing flows, tend to concentrate on learning the body of…

Machine Learning · Computer Science 2022-06-28 Mike Laszkiewicz , Johannes Lederer , Asja Fischer

Many complex networks in natural and social phenomena have often been characterized by heavy-tailed degree distributions. However, due to rapidly growing size of network data and concerns on privacy issues about using these data, it becomes…

Physics and Society · Physics 2015-05-19 Young-Ho Eom , Hang-Hyun Jo

Convergence in high-probability (HP) has attracted increasing interest, due to implying exponentially decaying tail bounds and strong guarantees for individual runs of an algorithm. While many works study HP guarantees in centralized…

Machine Learning · Computer Science 2026-05-22 Aleksandar Armacki , Ali H. Sayed

We consider stochastic convex optimization for heavy-tailed data with the guarantee of being differentially private (DP). Most prior works on differentially private stochastic convex optimization for heavy-tailed data are either restricted…

Machine Learning · Computer Science 2024-09-11 Chenhan Jin , Kaiwen Zhou , Bo Han , James Cheng , Tieyong Zeng

Training strategies for modern deep neural networks (NNs) tend to induce a heavy-tailed (HT) empirical spectral density (ESD) in the layer weights. While previous efforts have shown that the HT phenomenon correlates with good generalization…

Machine Learning · Computer Science 2025-08-12 Vignesh Kothapalli , Tianyu Pang , Shenyang Deng , Zongmin Liu , Yaoqing Yang

Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to…

Machine Learning · Computer Science 2017-01-17 Xi He , Dheevatsa Mudigere , Mikhail Smelyanskiy , Martin Takáč

A novel statistical method is proposed and investigated for estimating a heavy tailed density under mild smoothness assumptions. Statistical analyses of heavy-tailed distributions are susceptible to the problem of sparse information in the…

Methodology · Statistics 2022-11-18 Surya T Tokdar , Sheng Jiang , Erika L Cunningham

We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, as introduced by…

Machine Learning · Computer Science 2022-11-02 Gautam Kamath , Xingtu Liu , Huanyu Zhang

We study a scalable alternative to robust gradient descent (RGD) techniques that can be used when the gradients can be heavy-tailed, though this will be unknown to the learner. The core technique is simple: instead of trying to robustly…

Machine Learning · Statistics 2020-12-16 Matthew J. Holland

In real-world data, long-tailed data distribution is common, making it challenging for models trained on empirical risk minimisation to learn and classify tail classes effectively. While many studies have sought to improve long tail…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Ziheng Wang , Toni Lassila , Sharib Ali

The graduated optimization approach is a method for finding global optimal solutions for nonconvex functions by using a function smoothing operation with stochastic noise. This paper makes three contributions regarding graduated…

Machine Learning · Computer Science 2026-01-27 Naoki Sato , Hideaki Iiduka

The empirical evidence indicates that stochastic optimization with heavy-tailed gradient noise is more appropriate to characterize the training of machine learning models than that with standard bounded gradient variance noise. Most…

Machine Learning · Computer Science 2026-01-28 Hongxu Chen , Ke Wei , Xiaoming Yuan , Luo Luo

We study large deviation upper bounds and mean-squared error (MSE) guarantees of a general framework of nonlinear stochastic gradient methods in the online setting, in the presence of heavy-tailed noise. Unlike existing works that rely on…

Machine Learning · Computer Science 2025-03-25 Aleksandar Armacki , Shuhua Yu , Dragana Bajovic , Dusan Jakovetic , Soummya Kar

We consider the task of heavy-tailed statistical estimation given streaming $p$-dimensional samples. This could also be viewed as stochastic optimization under heavy-tailed distributions, with an additional $O(p)$ space complexity…

Machine Learning · Computer Science 2022-02-28 Che-Ping Tsai , Adarsh Prasad , Sivaraman Balakrishnan , Pradeep Ravikumar

Score-based model research in the last few years has produced state of the art generative models by employing Gaussian denoising score-matching (DSM). However, the Gaussian noise assumption has several high-dimensional limitations,…

Machine Learning · Computer Science 2022-04-13 Jacob Deasy , Nikola Simidjievski , Pietro Liò

We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze Stochastic Differential Equations (SDEs) that model SGD either…

Machine Learning · Computer Science 2024-07-03 Adrien Schertzer , Loucas Pillaud-Vivien