English
Related papers

Related papers: Second-order regression models exhibit progressive…

200 papers

During neural network training, the sharpness of the Hessian matrix of the training loss rises until training is on the edge of stability. As a result, even nonstochastic gradient descent does not accurately model the underlying dynamical…

Machine Learning · Statistics 2024-06-04 Mark Lowell , Catharine Kastner

Empirically it has been observed that the performance of deep neural networks steadily improves as we increase model size, contradicting the classical view on overfitting and generalization. Recently, the double descent phenomena has been…

Machine Learning · Computer Science 2021-07-28 Ilja Kuzborskij , Csaba Szepesvári , Omar Rivasplata , Amal Rannen-Triki , Razvan Pascanu

Recent works have examined theoretical and empirical properties of wide neural networks trained in the Neural Tangent Kernel (NTK) regime. Given that biological neural networks are much wider than their artificial counterparts, we consider…

Machine Learning · Computer Science 2022-07-14 Akhilan Boopathy , Ila Fiete

Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss…

Machine Learning · Computer Science 2025-11-18 Lawrence Wang , Stephen J. Roberts

Two key challenges facing modern deep learning are mitigating deep networks' vulnerability to adversarial attacks and understanding deep learning's generalization capabilities. Towards the first issue, many defense strategies have been…

Machine Learning · Computer Science 2022-10-24 Noel Loo , Ramin Hasani , Alexander Amini , Daniela Rus

The Neural Tangent Kernel (NTK) characterizes the behavior of infinitely wide neural nets trained under least squares loss by gradient descent. However, despite its importance, the super-quadratic runtime of kernel methods limits the use of…

Machine Learning · Computer Science 2021-07-28 Amir Zandieh

We show that accelerated gradient descent, averaged gradient descent and the heavy-ball method for non-strongly-convex problems may be reformulated as constant parameter second-order difference equation algorithms, where stability of the…

Machine Learning · Statistics 2015-04-08 Nicolas Flammarion , Francis Bach

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

Machine Learning · Statistics 2026-01-06 Haoran Zhan , Yingcun Xia

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

High-dimensional linear regression under heavy-tailed noise or outlier corruption is challenging, both computationally and statistically. Convex approaches have been proven statistically optimal but suffer from high computational costs,…

Statistics Theory · Mathematics 2023-05-11 Yinan Shen , Jingyang Li , Jian-Feng Cai , Dong Xia

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

We analyze the convergence of the averaged stochastic gradient descent for overparameterized two-layer neural networks for regression problems. It was recently found that a neural tangent kernel (NTK) plays an important role in showing the…

Machine Learning · Statistics 2021-06-14 Atsushi Nitanda , Taiji Suzuki

In wide neural networks, the Neural Tangent Kernel (NTK) remains approximately constant during training, providing a powerful theoretical tool for studying training dynamics, generalization, and connections to kernel methods. However, this…

Machine Learning · Computer Science 2026-05-26 Jonathan Plenk , Sergio Calvo-Ordonez , Alvaro Cartea , Yarin Gal , Mark van der Wilk , Kamil Ciosek

Recent findings by Cohen et al., 2021, demonstrate that when training neural networks using full-batch gradient descent with a step size of $\eta$, the largest eigenvalue $\lambda_{\max}$ of the full-batch Hessian consistently stabilizes…

Machine Learning · Computer Science 2025-12-30 Arseniy Andreyev , Pierfrancesco Beneventano

State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain…

Machine Learning · Statistics 2019-11-01 Alberto Bietti , Julien Mairal

When training neural networks with full-batch gradient descent (GD) and step size $\eta$, the largest eigenvalue of the Hessian -- the sharpness $S(\boldsymbol{\theta})$ -- rises to $2/\eta$ and hovers there, a phenomenon termed the Edge of…

Machine Learning · Computer Science 2026-04-24 Fangshuo Liao , Afroditi Kolomvaki , Anastasios Kyrillidis

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

The adversarial vulnerability of neural nets, and subsequent techniques to create robust models have attracted significant attention; yet we still lack a full understanding of this phenomenon. Here, we study adversarial examples of trained…

Machine Learning · Computer Science 2023-02-01 Nikolaos Tsilivis , Julia Kempe

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

Machine Learning · Computer Science 2024-11-19 Deqing Fu , Tian-Qi Chen , Robin Jia , Vatsal Sharan

This paper sheds new light on several interrelated topics of second-order variational analysis, both in finite and infinite-dimensional settings. We establish new relationships between second-order growth conditions on functions, the basic…

Optimization and Control · Mathematics 2013-04-30 D. Drusvyatskiy , B. S. Mordukhovich , T. T. A. Nghia