English
Related papers

Related papers: What can linearized neural networks actually say a…

200 papers

Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds considerable promise for improving predictions in machine learning. In this work, we aim to understand when and how deep networks -- with…

Machine Learning · Computer Science 2025-06-27 Andrea Perin , Stephane Deny

Deep Neural Networks can generalize despite being significantly overparametrized. Recent research has tried to examine this phenomenon from various view points and to provide bounds on the generalization error or measures predictive of the…

Machine Learning · Computer Science 2020-12-07 Parth Natekar , Manik Sharma

We prove that a randomly initialized neural network of *any architecture* has its Tangent Kernel (NTK) converge to a deterministic limit, as the network widths tend to infinity. We demonstrate how to calculate this limit. In prior…

Machine Learning · Statistics 2020-12-01 Greg Yang

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

State-of-the-art neural network training methods depend on the gradient of the network function. Therefore, they cannot be applied to networks whose activation functions do not have useful derivatives, such as binary and discrete-time…

Machine Learning · Statistics 2025-06-24 Luke Eilers , Raoul-Martin Memmesheimer , Sven Goedeke

Recently, quantum neural networks or quantum-classical neural networks (qcNN) have been actively studied, as a possible alternative to the conventional classical neural network (cNN), but their practical and theoretically-guaranteed…

Quantum Physics · Physics 2023-12-12 Kouhei Nakaji , Hiroyuki Tezuka , Naoki Yamamoto

We empirically evaluate common assumptions about neural networks that are widely held by practitioners and theorists alike. In this work, we: (1) prove the widespread existence of suboptimal local minima in the loss landscape of neural…

Machine Learning · Computer Science 2020-04-29 Micah Goldblum , Jonas Geiping , Avi Schwarzschild , Michael Moeller , Tom Goldstein

The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal initialization in linear networks has been well-proven.…

Machine Learning · Computer Science 2021-07-22 Wei Huang , Weitao Du , Richard Yi Da Xu

As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK…

Machine Learning · Computer Science 2022-07-18 Greg Yang , Edward J. Hu

We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture integrating Fourier…

Supervised deep learning involves the training of neural networks with a large number $N$ of parameters. For large enough $N$, in the so-called over-parametrized regime, one can essentially fit the training data points. Sparsity-based…

Disordered Systems and Neural Networks · Physics 2020-04-22 Mario Geiger , Arthur Jacot , Stefano Spigler , Franck Gabriel , Levent Sagun , Stéphane d'Ascoli , Giulio Biroli , Clément Hongler , Matthieu Wyart

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Graph neural networks (GNNs) achieve remarkable performance in graph machine learning tasks but can be hard to train on large-graph data, where their learning dynamics are not well understood. We investigate the training dynamics of…

Machine Learning · Computer Science 2023-06-02 Sanjukta Krishnagopal , Luana Ruiz

It has been recognized that heavily overparameterized deep neural networks (DNNs) exhibit surprisingly good generalization performance in various machine-learning tasks. Although benefits of depth have been investigated from different…

Machine Learning · Computer Science 2022-01-31 Takashi Mori , Masahito Ueda

As a general type of machine learning approach, artificial neural networks have established state-of-art benchmarks in many pattern recognition and data analysis tasks. Among various kinds of neural networks architectures, polynomial neural…

Machine Learning · Computer Science 2022-09-07 Chao Pan , Chuanyi Zhang

Overparameterized fully-connected neural networks have been shown to behave like kernel models when trained with gradient descent, under mild conditions on the width, the learning rate, and the parameter initialization. In the limit of…

Machine Learning · Computer Science 2025-11-11 William St-Arnaud , Margarida Carvalho , Golnoosh Farnadi

Matrix completion problems arise in many applications including recommendation systems, computer vision, and genomics. Increasingly larger neural networks have been successful in many of these applications, but at considerable computational…

Machine Learning · Computer Science 2022-05-11 Adityanarayanan Radhakrishnan , George Stefanakis , Mikhail Belkin , Caroline Uhler

The paper contains approximation guarantees for neural networks that are trained with gradient flow, with error measured in the continuous $L_2(\mathbb{S}^{d-1})$-norm on the $d$-dimensional unit sphere and targets that are Sobolev smooth.…

Machine Learning · Computer Science 2023-09-12 G. Welper

Modular neural networks outperform nonmodular neural networks on tasks ranging from visual question answering to robotics. These performance improvements are thought to be due to modular networks' superior ability to model the compositional…

Machine Learning · Computer Science 2025-03-12 Akhilan Boopathy , Sunshine Jiang , William Yue , Jaedong Hwang , Abhiram Iyer , Ila Fiete

In the era of large language models (LLMs), fine-tuning pretrained models has become ubiquitous. Yet the theoretical underpinning remains an open question. A central question is why only a few epochs of fine-tuning are typically sufficient…

Machine Learning · Statistics 2026-02-17 Zexuan Sun , Garvesh Raskutti