English
Related papers

Related papers: Better scalability under potentially heavy-tailed …

200 papers

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias. This bias is typically…

Machine Learning · Computer Science 2020-06-22 Ziwei Ji , Miroslav Dudík , Robert E. Schapire , Matus Telgarsky

Due to the massive size of the neural network models and training datasets used in machine learning today, it is imperative to distribute stochastic gradient descent (SGD) by splitting up tasks such as gradient evaluation across multiple…

Machine Learning · Computer Science 2020-03-13 Xiaoxi Zhang , Jianyu Wang , Gauri Joshi , Carlee Joe-Wong

Gradient descent algorithm is the most utilized method when optimizing machine learning issues. However, there exists many local minimums and saddle points in the loss function, especially for high dimensional non-convex optimization…

Machine Learning · Computer Science 2021-07-19 Zhicheng Cai

Both Byzantine resilience and communication efficiency have attracted tremendous attention recently for their significance in edge federated learning. However, most existing algorithms may fail when dealing with real-world irregular data…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-03-21 Youming Tao , Sijia Cui , Wenlu Xu , Haofei Yin , Dongxiao Yu , Weifa Liang , Xiuzhen Cheng

While stochastic gradient descent (SGD) is one of the major workhorses in machine learning, the learning properties of many practically used variants are poorly understood. In this paper, we consider least squares learning in a…

Machine Learning · Statistics 2019-05-28 Nicole Mücke , Gergely Neu , Lorenzo Rosasco

Adaptive optimization methods (such as Adam) play a major role in LLM pretraining, significantly outperforming Gradient Descent (GD). Recent studies have proposed new smoothness assumptions on the loss function to explain the advantages of…

Machine Learning · Computer Science 2025-12-02 Robin Yadav , Shuo Xie , Tianhao Wang , Zhiyuan Li

Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move…

Machine Learning · Computer Science 2021-08-27 Tong Wei , Jiang-Xin Shi , Wei-Wei Tu , Yu-Feng Li

Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead. This can be viewed as a hardware limitation (imposed by…

Machine Learning · Computer Science 2024-05-24 Kaelan Donatella , Samuel Duffield , Maxwell Aifer , Denis Melanson , Gavin Crooks , Patrick J. Coles

Stochastic first-order methods such as Stochastic Extragradient (SEG) or Stochastic Gradient Descent-Ascent (SGDA) for solving smooth minimax problems and, more generally, variational inequality problems (VIP) have been gaining a lot of…

Optimization and Control · Mathematics 2022-11-02 Eduard Gorbunov , Marina Danilova , David Dobre , Pavel Dvurechensky , Alexander Gasnikov , Gauthier Gidel

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empirical evidence…

Machine Learning · Computer Science 2025-07-03 Di Zhang , Yihang Zhang

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive…

Machine Learning · Statistics 2018-10-02 Qi Deng , Yi Cheng , Guanghui Lan

The performance of stochastic gradient descent (SGD) depends critically on how learning rates are tuned and decreased over time. We propose a method to automatically adjust multiple learning rates so as to minimize the expected error at any…

Machine Learning · Statistics 2013-02-19 Tom Schaul , Sixin Zhang , Yann LeCun

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

Machine Learning · Computer Science 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

Normalising flows are tractable probabilistic models that leverage the power of deep learning to describe a wide parametric family of distributions, all while remaining trainable using maximum likelihood. We discuss how these methods can be…

Machine Learning · Computer Science 2020-07-14 Simon Alexanderson , Gustav Eje Henter

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

Considered here are robust subgroup-classifier learning and testing in change-plane regressions with heavy-tailed errors, which can identify subgroups as a basis for making optimal recommendations for individualized treatment. A new…

Methodology · Statistics 2024-08-27 Xu Liu , Jian Huang , Yong Zhou , Xiao Zhang

In recent works on the theory of machine learning, it has been observed that heavy tail properties of Stochastic Gradient Descent (SGD) can be studied in the probabilistic framework of stochastic recursions. In particular,…

Machine Learning · Statistics 2024-03-22 Ewa Damek , Sebastian Mentemeier

We consider a standard distributed optimization problem in which networked nodes collaboratively minimize the sum of their locally known convex costs. For this setting, we address for the first time the fundamental problem of design and…

Optimization and Control · Mathematics 2025-06-02 Manojlo Vukovic , Dusan Jakovetic , Dragana Bajovic , Soummya Kar

Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Shenghan Chen , Yiming Liu , Yanzhen Wang , Yujia Wang , Xiankai Lu

Learning with a {\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper,…

Machine Learning · Computer Science 2018-05-22 Yi Xu , Shenghuo Zhu , Sen Yang , Chi Zhang , Rong Jin , Tianbao Yang
‹ Prev 1 4 5 6 7 8 10 Next ›