English
Related papers

Related papers: A Scale Invariant Flatness Measure for Deep Networ…

200 papers

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

Flat minima are strongly associated with improved generalisation in deep neural networks. However, this connection has proven nuanced in recent studies, with both theoretical counterexamples and empirical exceptions emerging in the…

Machine Learning · Computer Science 2026-04-16 Israel Mason-Williams , Gabryel Mason-Williams , Helen Yannakoudakis

It was empirically confirmed by Keskar et al.\cite{SharpMinima} that flatter minima generalize better. However, for the popular ReLU network, sharp minimum can also generalize well \cite{SharpMinimacan}. The conclusion demonstrates that the…

Machine Learning · Computer Science 2019-03-07 Mingyang Yi , Qi Meng , Wei Chen , Zhi-ming Ma , Tie-Yan Liu

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

Machine Learning · Statistics 2019-11-12 Talha Cihad Gulcu

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain linear transformations…

Machine Learning · Computer Science 2020-03-03 Difan Zou , Philip M. Long , Quanquan Gu

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Recent works have highlighted scale invariance or symmetry that is present in the weight space of a typical deep network and the adverse effect that it has on the Euclidean gradient based stochastic gradient descent optimization. In this…

Machine Learning · Computer Science 2015-11-10 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

A large body of theory and empirical work hypothesizes a connection between the flatness of a neural network's loss landscape during training and its performance. However, there have been conceptually opposite pieces of evidence regarding…

Machine Learning · Computer Science 2026-02-06 Yizhou Xu , Pierfrancesco Beneventano , Isaac Chuang , Liu Ziyin

Despite extensive study, the significance of sharpness -- the trace of the loss Hessian at local minima -- remains unclear. We investigate an alternative perspective: how sharpness relates to the geometric structure of neural…

Machine Learning · Computer Science 2026-02-24 Shirui Chen , Stefano Recanatesi , Eric Shea-Brown

Recently, it has been observed that when training a deep neural net with SGD, the majority of the loss landscape's curvature quickly concentrates in a tiny *top* eigenspace of the loss Hessian, which remains largely stable thereafter.…

Machine Learning · Computer Science 2025-04-22 Andres Fernandez , Frank Schneider , Maren Mahsereci , Philipp Hennig

Despite the non-convex nature of their loss functions, deep neural networks are known to generalize well when optimized with stochastic gradient descent (SGD). Recent work conjectures that SGD with proper configuration is able to find wide…

Machine Learning · Computer Science 2019-04-09 Haowei He , Gao Huang , Yang Yuan

Understanding the properties of well-generalizing minima is at the heart of deep learning research. On the one hand, the generalization of neural networks has been connected to the decision boundary complexity, which is hard to study in the…

Machine Learning · Computer Science 2023-06-13 Mahalakshmi Sabanayagam , Freya Behrens , Urte Adomaityte , Anna Dawid

The phenomenon that stochastic gradient descent (SGD) favors flat minima has played a critical role in understanding the implicit regularization of SGD. In this paper, we provide an explanation of this striking phenomenon by relating the…

Machine Learning · Statistics 2022-10-18 Lei Wu , Mingze Wang , Weijie Su

We consider Sharpness-Aware Minimization (SAM), a gradient-based optimization method for deep networks that has exhibited performance improvements on image and language prediction problems. We show that when SAM is applied with a convex…

Machine Learning · Computer Science 2023-04-12 Peter L. Bartlett , Philip M. Long , Olivier Bousquet

Model reparametrization, which follows the change-of-variable rule of calculus, is a popular way to improve the training of neural nets. But it can also be problematic since it can induce inconsistencies in, e.g., Hessian-based flatness…

Machine Learning · Computer Science 2023-10-24 Agustinus Kristiadi , Felix Dangel , Philipp Hennig

We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results…

Machine Learning · Computer Science 2019-06-04 Vardan Papyan

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

By using the viewpoint of modern computational algebraic geometry, we explore properties of the optimization landscapes of the deep linear neural network models. After clarifying on the various definitions of "flat" minima, we show that the…

Machine Learning · Statistics 2018-10-19 Dhagash Mehta , Tianran Chen , Tingting Tang , Jonathan D. Hauenstein

This paper studies the effect of data homogeneity on multi-agent stochastic optimization. We consider the decentralized stochastic gradient (DSGD) algorithm and perform a refined convergence analysis. Our analysis is explicit on the…

Optimization and Control · Mathematics 2024-09-09 Qiang Li , Hoi-To Wai

Stochastic Gradient Descent (SGD) stands as a cornerstone optimization algorithm with proven real-world empirical successes but relatively limited theoretical understanding. Recent research has illuminated a key factor contributing to its…

Machine Learning · Computer Science 2024-01-24 Gregory Dexter , Borja Ocejo , Sathiya Keerthi , Aman Gupta , Ayan Acharya , Rajiv Khanna