English
Related papers

Related papers: Eigenvalues of the Hessian in Deep Learning: Singu…

200 papers

Recent work has highlighted a surprising alignment between gradients and the top eigenspace of the Hessian -- termed the Dominant subspace -- during neural network training. Concurrently, there has been growing interest in the distinct…

Machine Learning · Computer Science 2025-05-20 Daniyar Zakarin , Sidak Pal Singh

A fundamental question in deep learning concerns the role played by individual layers in a deep neural network (DNN) and the transferable properties of the data representations which they learn. To the extent that layers have clear roles,…

Machine Learning · Computer Science 2019-06-14 Oded Ben-David , Zohar Ringel

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Neural and Evolutionary Computing · Computer Science 2024-11-06 Mathew Mithra Noel , Arindam Banerjee , Yug Oswal , Geraldine Bessie Amali D , Venkataraman Muthiah-Nakarajan

Recent work has shown that methods like SAM which either explicitly or implicitly penalize second order information can improve generalization in deep learning. Seemingly similar methods like weight noise and gradient penalties often fail…

Machine Learning · Computer Science 2024-01-26 Yann N. Dauphin , Atish Agarwala , Hossein Mobahi

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…

Machine Learning · Statistics 2019-05-28 Soufiane Hayou , Arnaud Doucet , Judith Rousseau

We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets.…

Machine Learning · Computer Science 2021-12-28 Nicholas P Baskerville , Diego Granziol , Jonathan P Keating

Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not completely understood. Here, we study large batch size training…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Qi Lei , Kurt Keutzer , Michael W. Mahoney

The loss landscape of neural networks is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we investigate how the loss surface changes when the sample size…

Machine Learning · Computer Science 2024-09-19 Nikita Kiselev , Andrey Grabovoy

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

We consider Bayesian inverse problems wherein the unknown state is assumed to be a function with discontinuous structure a priori. A class of prior distributions based on the output of neural networks with heavy-tailed weights is…

Machine Learning · Computer Science 2021-12-21 Chen Li , Matthew Dunlop , Georg Stadler

This paper illustrates the central role of loss functions in data-driven decision making, providing a comprehensive survey on their influence in cost-sensitive classification (CSC) and reinforcement learning (RL). We demonstrate how…

Machine Learning · Statistics 2025-04-07 Kaiwen Wang , Nathan Kallus , Wen Sun

The Hessian spectrum of trained deep networks exhibits a characteristic structure: a continuous bulk of near-zero eigenvalues and a small number of large outlier eigenvalues (spikes), confirming the relevance of Random Matrix Theory in deep…

Machine Learning · Computer Science 2026-05-19 Hugo Vigna , Samuel Bontemps

Traditional analyses of gradient descent show that when the largest eigenvalue of the Hessian, also known as the sharpness $S(\theta)$, is bounded by $2/\eta$, training is "stable" and the training loss decreases monotonically. Recent…

Machine Learning · Computer Science 2023-04-12 Alex Damian , Eshaan Nichani , Jason D. Lee

Deep neural networks trained using gradient descent with a fixed learning rate $\eta$ often operate in the regime of "edge of stability" (EOS), where the largest eigenvalue of the Hessian equilibrates about the stability threshold $2/\eta$.…

Machine Learning · Statistics 2025-03-03 Avrajit Ghosh , Soo Min Kwon , Rongrong Wang , Saiprasad Ravishankar , Qing Qu

We consider the linear damped wave equation on finite metric graphs and analyse its spectral properties with an emphasis on the asymptotic behaviour of eigenvalues. In the case of equilateral graphs and standard coupling conditions we show…

Mathematical Physics · Physics 2017-02-16 Pedro Freitas , Jiri Lipovsky

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics. Whereas prior work has focused on how different learning…

Parameter ensembles or sets of point estimates constitute one of the cornerstones of modern statistical practice. This is especially the case in Bayesian hierarchical models, where different decision-theoretic frameworks can be deployed to…

Methodology · Statistics 2011-06-10 Cedric E. Ginestet , Nicky G. Best , Sylvia Richardson

Stochastic gradient descent (SGD) is widely used in deep learning due to its computational efficiency, but a complete understanding of why SGD performs so well remains a major challenge. It has been observed empirically that most…

Machine Learning · Statistics 2022-06-20 Carmina Fjellström , Kaj Nyström

This paper is a tutorial for eigenvalue and generalized eigenvalue problems. We first introduce eigenvalue problem, eigen-decomposition (spectral decomposition), and generalized eigenvalue problem. Then, we mention the optimization problems…

Machine Learning · Statistics 2023-05-23 Benyamin Ghojogh , Fakhri Karray , Mark Crowley

Edge computing has gained significant traction in recent years, promising enhanced efficiency by integrating artificial intelligence capabilities at the edge. While the focus has primarily been on the deployment and inference of Machine…

Machine Learning · Computer Science 2024-10-14 Aymen Rayane Khouas , Mohamed Reda Bouadjenek , Hakim Hacid , Sunil Aryal