English
Related papers

Related papers: Changing the Kernel During Training Leads to Doubl…

200 papers

Epoch-wise double descent is the phenomenon where generalisation performance improves beyond the point of overfitting, resulting in a generalisation curve exhibiting two descents under the course of learning. Understanding the mechanisms…

Machine Learning · Statistics 2024-09-20 Amanda Olmin , Fredrik Lindsten

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

Gradient descent yields zero training loss in polynomial time for deep neural networks despite non-convex nature of the objective function. The behavior of network in the infinite width limit trained by gradient descent can be described by…

Machine Learning · Computer Science 2023-05-29 Yuqing Li , Tao Luo , Nung Kwan Yip

Recent research has been focused on two different approaches to studying neural networks training in the limit of infinite width (1) a mean-field (MF) and (2) a constant neural tangent kernel (NTK) approximations. These two approaches have…

Machine Learning · Computer Science 2020-10-23 Eugene A. Golikov

Two distinct limits for deep learning have been derived as the network width $h\rightarrow \infty$, depending on how the weights of the last layer scale with $h$. In the Neural Tangent Kernel (NTK) limit, the dynamics becomes linear in the…

Machine Learning · Computer Science 2020-12-30 Mario Geiger , Stefano Spigler , Arthur Jacot , Matthieu Wyart

This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory. It is well known that as the network's width tends to…

Machine Learning · Statistics 2024-10-10 Guhan Chen , Yicheng Li , Qian Lin

We study the relative power of learning with gradient descent on differentiable models, such as neural networks, versus using the corresponding tangent kernels. We show that under certain conditions, gradient descent achieves small error…

Machine Learning · Computer Science 2021-03-02 Eran Malach , Pritish Kamath , Emmanuel Abbe , Nathan Srebro

Generalization performance of classifiers in deep learning has recently become a subject of intense study. Deep models, typically over-parametrized, tend to fit the training data exactly. Despite this "overfitting", they perform well on…

Machine Learning · Statistics 2018-06-18 Mikhail Belkin , Siyuan Ma , Soumik Mandal

We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-parameterized linear regression models using gradient descent with weight…

Machine Learning · Computer Science 2026-02-09 Mingyue Xu , Gal Vardi , Itay Safran

The primary hyperparameter in kernel regression (KR) is the choice of kernel. In most theoretical studies of KR, one assumes the kernel is fixed before seeing the training data. Under this assumption, it is known that the optimal kernel is…

Machine Learning · Computer Science 2022-09-28 James B. Simon

The distribution regression problem encompasses many important statistics and machine learning tasks, and arises in a large range of applications. Among various existing approaches to tackle this problem, kernel methods have become a method…

Statistics Theory · Mathematics 2025-09-22 François Bachoc , Louis Béthune , Alberto González-Sanz , Jean-Michel Loubes

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

We consider learning two layer neural networks using stochastic gradient descent. The mean-field description of this learning dynamics approximates the evolution of the network weights by an evolution in the space of probability…

Machine Learning · Statistics 2019-02-19 Song Mei , Theodor Misiakiewicz , Andrea Montanari

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

Machine Learning · Computer Science 2014-06-17 Francesco Orabona

Recent theoretical studies (Kou et al., 2023; Cao et al., 2022) have revealed a sharp phase transition from benign to harmful overfitting when the noise-to-feature ratio exceeds a threshold-a situation common in long-tailed data…

Machine Learning · Computer Science 2025-06-10 Ruichen Xu , Kexin Chen

Kernel ridge regression is well-known to achieve minimax optimal rates in low-dimensional settings. However, its behavior in high dimensions is much less understood. Recent work establishes consistency for kernel regression under certain…

Statistics Theory · Mathematics 2021-04-12 Konstantin Donhauser , Mingqi Wu , Fanny Yang

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even…

Machine Learning · Computer Science 2022-06-20 Zheng He , Zeke Xie , Quanzhi Zhu , Zengchang Qin

Existing statistical learning guarantees for general kernel regressors often yield loose bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in several machine learning problems, e.g.\ when fine-tuning a…

Machine Learning · Computer Science 2023-10-04 Tin Sum Cheng , Aurelien Lucchi , Ivan Dokmanić , Anastasis Kratsios , David Belius

We consider the problem of streaming kernel regression, when the observations arrive sequentially and the goal is to recover the underlying mean function, assumed to belong to an RKHS. The variance of the noise is not assumed to be known.…

Machine Learning · Statistics 2017-08-03 Audrey Durand , Odalric-Ambrym Maillard , Joelle Pineau