English
Related papers

Related papers: Classifying high-dimensional Gaussian mixtures: Wh…

200 papers

It has been observed \citep{zhang2016understanding} that deep neural networks can memorize: they achieve 100\% accuracy on training data. Recent theoretical results explained such behavior in highly overparametrized regimes, where the…

Machine Learning · Computer Science 2019-09-27 Rong Ge , Runzhe Wang , Haoyu Zhao

Previous research has shown that fully-connected networks with small initialization and gradient-based training methods exhibit a phenomenon known as condensation during training. This phenomenon refers to the input weights of hidden…

Machine Learning · Computer Science 2023-05-18 Zhangchen Zhou , Hanxu Zhou , Yuqing Li , Zhi-Qin John Xu

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang

It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what…

Machine Learning · Computer Science 2018-11-30 Liwei Wang , Lunjia Hu , Jiayuan Gu , Yue Wu , Zhiqiang Hu , Kun He , John Hopcroft

A well-recognized limitation of kernel learning is the requirement to handle a kernel matrix, whose size is quadratic in the number of training examples. Many methods have been proposed to reduce this computational cost, mostly by using a…

Machine Learning · Computer Science 2014-11-06 Nicolò Cesa-Bianchi , Yishay Mansour , Ohad Shamir

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

Combining Gaussian processes with the expressive power of deep neural networks is commonly done nowadays through deep kernel learning (DKL). Unfortunately, due to the kernel optimization process, this often results in losing their Bayesian…

Machine Learning · Computer Science 2023-05-16 Idan Achituve , Gal Chechik , Ethan Fetaya

Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is…

Machine Learning · Computer Science 2012-07-03 Mehmet Gonen

In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussian Multi-index model…

Machine Learning · Statistics 2026-02-06 Bohan Zhang , Zihao Wang , Hengyu Fu , Jason D. Lee

Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and…

Machine Learning · Computer Science 2017-03-28 Sek Chai , Aswin Raghavan , David Zhang , Mohamed Amer , Tim Shields

The impressive practical performance of neural networks is often attributed to their ability to learn low-dimensional data representations and hierarchical structure directly from data. In this work, we argue that these two phenomena are…

Machine Learning · Statistics 2025-10-06 Libin Zhu , Damek Davis , Dmitriy Drusvyatskiy , Maryam Fazel

Recent work has argued that neural networks can be understood theoretically by taking the number of channels to infinity, at which point the outputs become Gaussian process (GP) distributed. However, we note that infinite Bayesian neural…

Machine Learning · Statistics 2020-06-25 Laurence Aitchison

We prove that a particular deep network architecture is more efficient at approximating radially symmetric functions than the best known 2 or 3 layer networks. We use this architecture to approximate Gaussian kernel SVMs, and subsequently…

Machine Learning · Computer Science 2017-03-13 Brendan McCane , Lech Szymanski

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge:…

Machine Learning · Statistics 2022-10-13 Leonardo Petrini , Francesco Cagnetta , Eric Vanden-Eijnden , Matthieu Wyart

In this paper, we consider parameter recovery for non-overlapping convolutional neural networks (CNNs) with multiple kernels. We show that when the inputs follow Gaussian distribution and the sample size is sufficiently large, the squared…

Machine Learning · Computer Science 2017-11-10 Kai Zhong , Zhao Song , Inderjit S. Dhillon

We perform a careful, thorough, and large scale empirical study of the correspondence between wide neural networks and kernel methods. By doing so, we resolve a variety of open questions related to the study of infinitely wide neural…

Machine Learning · Computer Science 2020-09-09 Jaehoon Lee , Samuel S. Schoenholz , Jeffrey Pennington , Ben Adlam , Lechao Xiao , Roman Novak , Jascha Sohl-Dickstein

In this era of artificial intelligence, deep neural networks like Convolutional Neural Networks (CNNs) have emerged as front-runners, often surpassing human capabilities. These deep networks are often perceived as the panacea for all…

Computer Vision and Pattern Recognition · Computer Science 2023-11-15 Neeraj Kumar Singh , Nikhil R. Pal

We show that the output of a (residual) convolutional neural network (CNN) with an appropriate prior over the weights and biases is a Gaussian process (GP) in the limit of infinitely many convolutional filters, extending similar results for…

Machine Learning · Statistics 2019-05-07 Adrià Garriga-Alonso , Carl Edward Rasmussen , Laurence Aitchison

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks. State-of-the-art methods favor such deep network architectures for its accuracy performance, with the cost of having massive…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Jiahui Huang , Kshitij Dwivedi , Gemma Roig
‹ Prev 1 3 4 5 6 7 10 Next ›