English
Related papers

Related papers: GLASD: A Loss-Function-Agnostic Global Optimizer f…

200 papers

Stochastic gradient descent (SGD) method is popular for solving non-convex optimization problems in machine learning. This work investigates SGD from a viewpoint of graduated optimization, which is a widely applied approach for non-convex…

Optimization and Control · Mathematics 2023-08-15 Da Li , Jingjing Wu , Qingrun Zhang

Black-box algorithms are designed to optimize functions without relying on their underlying analytical structure or gradient information, making them essential when gradients are inaccessible or difficult to compute. Traditional methods for…

Machine Learning · Computer Science 2026-01-21 Yedidya Kfir , Elad Sarafian , Sarit Kraus , Yoram Louzoun

Modern supervised learning techniques, particularly those using deep nets, involve fitting high dimensional labelled data sets with functions containing very large numbers of parameters. Much of this work is empirical. Interesting phenomena…

Machine Learning · Statistics 2018-05-30 Partha P Mitra

This paper presents a new generalization error analysis for Decentralized Stochastic Gradient Descent (D-SGD) based on algorithmic stability. The obtained results overhaul a series of recent works that suggested an increased instability due…

Machine Learning · Computer Science 2024-06-14 Batiste Le Bars , Aurélien Bellet , Marc Tommasi , Kevin Scaman , Giovanni Neglia

Gaussian Graphical Models (GGMs) are popular tools for studying network structures. However, many modern applications such as gene network discovery and social interactions analysis often involve high-dimensional noisy data with outliers or…

Machine Learning · Statistics 2015-10-30 Eunho Yang , Aurélie C. Lozano

The generalised linear model (GLM) is a very important tool for analysing real data in biology, sociology, agriculture, engineering and many other application domain where the relationship between the response and explanatory variables may…

Methodology · Statistics 2016-07-04 Abhik Ghosh , Ayanendranath Basu

Many Machine Learning algorithms are formulated as regularized optimization problems, but their performance hinges on a regularization parameter that needs to be calibrated to each application at hand. In this paper, we propose a general…

Machine Learning · Statistics 2021-03-31 Mike Laszkiewicz , Asja Fischer , Johannes Lederer

While low-precision optimization has been widely used to accelerate deep learning, low-precision sampling remains largely unexplored. As a consequence, sampling is simply infeasible in many large-scale scenarios, despite providing…

Machine Learning · Computer Science 2022-06-22 Ruqi Zhang , Andrew Gordon Wilson , Christopher De Sa

Gradient clipping is a commonly used technique to stabilize the training process of neural networks. A growing body of studies has shown that gradient clipping is a promising technique for dealing with the heavy-tailed behavior that emerged…

Machine Learning · Computer Science 2023-07-26 Shaojie Li , Yong Liu

We establish a data-dependent notion of algorithmic stability for Stochastic Gradient Descent (SGD), and employ it to develop novel generalization bounds. This is in contrast to previous distribution-free algorithmic stability results for…

Machine Learning · Computer Science 2018-02-19 Ilja Kuzborskij , Christoph H. Lampert

Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority. This task is widely applied in various real-world scenarios,…

Machine Learning · Computer Science 2025-07-03 Xiang Li , Jianpeng Qi , Zhongying Zhao , Guanjie Zheng , Lei Cao , Junyu Dong , Yanwei Yu

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

In recent years, stochastic gradient descent (SGD) methods and randomized linear algebra (RLA) algorithms have been applied to many large-scale problems in machine learning and data analysis. We aim to bridge the gap between these two…

Optimization and Control · Mathematics 2017-07-11 Jiyan Yang , Yin-Lam Chow , Christopher Ré , Michael W. Mahoney

This paper examines the role and efficiency of the non-convex loss functions for binary classification problems. In particular, we investigate how to design a simple and effective boosting algorithm that is robust to the outliers in the…

Machine Learning · Statistics 2017-08-25 Alexander Hanbo Li , Jelena Bradic

Heavy-tailed noise in nonconvex stochastic optimization has garnered increasing research interest, as empirical studies, including those on training attention models, suggest it is a more realistic gradient noise condition. This paper…

Optimization and Control · Mathematics 2026-04-17 Shuhua Yu , Dusan Jakovetic , Soummya Kar

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Beier Zhu , Kaihua Tang , Qianru Sun , Hanwang Zhang

We study the generalization properties of the popular stochastic optimization method known as stochastic gradient descent (SGD) for optimizing general non-convex loss functions. Our main contribution is providing upper bounds on the…

Machine Learning · Computer Science 2021-08-17 Gergely Neu , Gintare Karolina Dziugaite , Mahdi Haghifam , Daniel M. Roy

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be…

Machine Learning · Computer Science 2023-11-07 Zhilin Zhao , Longbing Cao , Chang-Dong Wang

It is known that the Thresholded Lasso (TL), SCAD or MCP correct intrinsic estimation bias of the Lasso. In this paper we propose an alternative method of improving the Lasso for predictive models with general convex loss functions which…

Statistics Theory · Mathematics 2021-01-26 Piotr Pokarowski , Wojciech Rejchel , Agnieszka Soltys , Michal Frej , Jan Mielniczuk

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
‹ Prev 1 4 5 6 7 8 10 Next ›