English
Related papers

Related papers: On the Power-Law Hessian Spectrums in Deep Learnin…

200 papers

Loss landscape analysis is extremely useful for a deeper understanding of the generalization ability of deep neural network models. In this work, we propose a layerwise loss landscape analysis where the loss surface at every layer is…

Machine Learning · Computer Science 2020-12-09 Adepu Ravi Sankar , Yash Khasbage , Rahul Vigneswaran , Vineeth N Balasubramanian

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

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

Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between…

Machine Learning · Statistics 2019-02-25 Felix Draxler , Kambis Veschgini , Manfred Salmhofer , Fred A. Hamprecht

Neural scaling laws describe how the performance of deep neural networks scales with key factors such as training data size, model complexity, and training time, often following power-law behaviors over multiple orders of magnitude. Despite…

Machine Learning · Statistics 2024-10-14 Roman Worschech , Bernd Rosenow

Despite the widespread adoption of neural networks, their training dynamics remain poorly understood. We show experimentally that as the size of the dataset increases, a point forms where the magnitude of the gradient of the loss becomes…

Machine Learning · Computer Science 2024-07-23 Mark Lowell

Recently, there has been growing evidence that if the width and depth of a neural network are scaled toward the so-called rich feature learning limit (\mup and its depth extension), then some hyperparameters -- such as the learning rate --…

Machine Learning · Computer Science 2024-11-14 Lorenzo Noci , Alexandru Meterez , Thomas Hofmann , Antonio Orvieto

Empirical studies reported that the Hessian matrix of neural networks (NNs) exhibits a near-block-diagonal structure, yet its theoretical foundation remains unclear. In this work, we reveal that the reported Hessian structure comes from a…

Machine Learning · Computer Science 2025-09-23 Zhaorui Dong , Yushun Zhang , Jianfeng Yao , Ruoyu Sun

Given an optimization problem, the Hessian matrix and its eigenspectrum can be used in many ways, ranging from designing more efficient second-order algorithms to performing model analysis and regression diagnostics. When nonlinear models…

Machine Learning · Statistics 2021-03-18 Zhenyu Liao , Michael W. Mahoney

Power-law scaling, a central concept in critical phenomena, is found to be useful in deep learning, where optimized test errors on handwritten digit examples converge as a power-law to zero with database size. For rapid decision making with…

Machine Learning · Computer Science 2022-11-17 Yuval Meir , Shira Sardi , Shiri Hodassman , Karin Kisos , Itamar Ben-Noam , Amir Goldental , Ido Kanter

Interacting many-body physical systems ranging from neural networks in the brain to folding proteins to self-modifying electrical circuits can learn to perform diverse tasks. This learning, both in nature and in engineered systems, can…

Disordered Systems and Neural Networks · Physics 2024-02-22 Menachem Stern , Andrea J. Liu , Vijay Balasubramanian

We investigate why deep neural networks suffer from loss of plasticity in deep continual learning, failing to learn new tasks without reinitializing parameters. We show that this failure is preceded by Hessian spectral collapse at new-task…

Machine Learning · Computer Science 2025-09-30 Naicheng He , Kaicheng Guo , Arjun Prakash , Saket Tiwari , Ruo Yu Tao , Tyrone Serapio , Amy Greenwald , George Konidaris

Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmetries in neural networks and show that overparameterization…

Machine Learning · Computer Science 2026-05-11 Kusha Sareen , Mohammad Pedramfar , Sékou-Oumar Kaba , Mehran Shakerinava , Siamak Ravanbakhsh

Neural networks (NNs) are central to modern machine learning and achieve state-of-the-art results in many applications. However, the relationship between loss geometry and generalization is still not well understood. The local geometry of…

Machine Learning · Computer Science 2026-04-15 Yuto Omae , Kazuki Sakai , Yohei Kakimoto , Makoto Sasaki , Yusuke Sakai , Hirotaka Takahashi

`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized. The current theoretical understanding behind the occurrence of this phenomenon is primarily based on…

Machine Learning · Statistics 2022-03-15 Sidak Pal Singh , Aurelien Lucchi , Thomas Hofmann , Bernhard Schölkopf

Hyperparameter optimization is an important subfield of machine learning that focuses on tuning the hyperparameters of a chosen algorithm to achieve peak performance. Recently, there has been a stream of methods that tackle the issue of…

Machine Learning · Computer Science 2023-10-26 Arlind Kadra , Maciej Janowski , Martin Wistuba , Josif Grabocka

Ensembles of deep neural networks are known to achieve state-of-the-art performance in uncertainty estimation and lead to accuracy improvement. In this work, we focus on a classification problem and investigate the behavior of both…

Machine Learning · Computer Science 2021-06-29 Ekaterina Lobacheva , Nadezhda Chirkova , Maxim Kodryan , Dmitry Vetrov

For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capacity to tackle deep learning models capturing rich feature learning effects, thus going beyond the…

Machine Learning · Statistics 2025-12-15 Jean Barbier , Francesco Camilli , Minh-Toan Nguyen , Mauro Pastore , Rudy Skerk

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

Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear models. In this work, we present a systematic analysis of scaling laws for quadratic and…