English
Related papers

Related papers: Implicit Bias of MSE Gradient Optimization in Unde…

200 papers

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

It has been recognized that a heavily overparameterized artificial neural network exhibits surprisingly good generalization performance in various machine-learning tasks. Recent theoretical studies have made attempts to unveil the mystery…

Machine Learning · Computer Science 2021-01-28 Takashi Mori , Masahito Ueda

The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding exponential convergence guarantees. However, existing results are often overly pessimistic…

Machine Learning · Computer Science 2026-05-26 Ruchirinkil Marreddy , Chaoyue Liu

We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples using theoretical methods from Gaussian processes and statistical physics. Our expressions apply to…

Machine Learning · Computer Science 2021-02-26 Blake Bordelon , Abdulkadir Canatar , Cengiz Pehlevan

Previous work has cast doubt on the general framework of uniform convergence and its ability to explain generalization in neural networks. By considering a specific dataset, it was observed that a neural network completely misclassifies a…

Machine Learning · Computer Science 2021-09-01 Gregor Bachmann , Seyed-Mohsen Moosavi-Dezfooli , Thomas Hofmann

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining…

Machine Learning · Computer Science 2023-06-01 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Francesco Locatello , Volkan Cevher

Deep residual network architectures have been shown to achieve superior accuracy over classical feed-forward networks, yet their success is still not fully understood. Focusing on massively over-parameterized, fully connected residual…

Machine Learning · Computer Science 2021-04-08 Yuval Belfer , Amnon Geifman , Meirav Galun , Ronen Basri

Neural Tangent Kernel (NTK) theory is widely used to study the dynamics of infinitely-wide deep neural networks (DNNs) under gradient descent. But do the results for infinitely-wide networks give us hints about the behavior of real…

Machine Learning · Computer Science 2022-02-02 Mariia Seleznova , Gitta Kutyniok

We analyze the generalization properties of two-layer neural networks in the neural tangent kernel (NTK) regime, trained with gradient descent (GD). For early stopped GD we derive fast rates of convergence that are known to be minimax…

Machine Learning · Statistics 2023-09-18 Mike Nguyen , Nicole Mücke

Larger and deeper networks generalise well despite their increased capacity to overfit. Understanding why this happens is theoretically and practically important. One recent approach looks at the infinitely wide limits of such networks and…

Machine Learning · Computer Science 2023-10-13 Adrian Goldwaser , Hong Ge

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

In suitably initialized wide networks, small learning rates transform deep neural networks (DNNs) into neural tangent kernel (NTK) machines, whose training dynamics is well-approximated by a linear weight expansion of the network at…

Machine Learning · Computer Science 2020-10-29 Stanislav Fort , Gintare Karolina Dziugaite , Mansheej Paul , Sepideh Kharaghani , Daniel M. Roy , Surya Ganguli

Neural networks typically generalize well when fitting the data perfectly, even though they are heavily overparameterized. Many factors have been pointed out as the reason for this phenomenon, including an implicit bias of stochastic…

Machine Learning · Computer Science 2025-02-04 Amit Peleg , Matthias Hein

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

Different gradient-based methods for optimizing overparameterized models can all achieve zero training error yet converge to distinctly different solutions inducing different generalization properties. We provide the first complete…

Machine Learning · Computer Science 2025-12-08 Chen Fan , Mark Schmidt , Christos Thrampoulidis

Computing eigenvalue decomposition (EVD) of a given linear operator, or finding its leading eigenvalues and eigenfunctions, is a fundamental task in many machine learning and scientific computing problems. For high-dimensional eigenvalue…

Machine Learning · Computer Science 2024-08-22 J. Jon Ryu , Xiangxiang Xu , H. S. Melihcan Erol , Yuheng Bu , Lizhong Zheng , Gregory W. Wornell

We focus on semiparametric regression that has played a central role in statistics, and exploit the powerful learning ability of deep neural networks (DNNs) while enabling statistical inference on parameters of interest that offers…

Statistics Theory · Mathematics 2025-04-29 Shunxing Yan , Ziyuan Chen , Fang Yao

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To…

Machine Learning · Computer Science 2023-03-09 William Merrill , Vivek Ramanujan , Yoav Goldberg , Roy Schwartz , Noah Smith

Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving manner without the aid of a central server. Neural network…

Machine Learning · Computer Science 2025-04-23 Shreyas Chaudhari , Srinivasa Pranav , Emile Anand , José M. F. Moura
‹ Prev 1 3 4 5 6 7 10 Next ›