English
Related papers

Related papers: A jamming transition from under- to over-parametri…

200 papers

Classical regression has a simple geometric description in terms of a projection of the training labels onto the column space of the design matrix. However, for over-parameterized models -- where the number of fit parameters is large enough…

Machine Learning · Statistics 2021-04-28 Jason W. Rocks , Pankaj Mehta

We study the generalization behavior of transfer learning of deep neural networks (DNNs). We adopt the overparameterization perspective -- featuring interpolation of the training data (i.e., approximately zero train error) and the double…

Machine Learning · Computer Science 2023-06-13 Yehuda Dar , Lorenzo Luzi , Richard G. Baraniuk

We propose that the grokking phenomenon, where the train loss of a neural network decreases much earlier than its test loss, can arise due to a neural network transitioning from lazy training dynamics to a rich, feature learning regime. To…

Machine Learning · Statistics 2024-04-12 Tanishq Kumar , Blake Bordelon , Samuel J. Gershman , Cengiz Pehlevan

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

Recent research on the grokking phenomenon has illuminated the intricacies of neural networks' training dynamics and their generalization behaviors. Grokking refers to a sharp rise of the network's generalization accuracy on the test set,…

Machine Learning · Computer Science 2024-05-31 Simin Fan , Razvan Pascanu , Martin Jaggi

Overfit is a fundamental problem in machine learning in general, and in deep learning in particular. In order to reduce overfit and improve generalization in the classification of images, some employ invariance to a group of…

Machine Learning · Computer Science 2021-02-12 Roee Cates , Daphna Weinshall

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe

While overfitting and, more generally, double descent are ubiquitous in machine learning, increasing the number of parameters of the most widely used tensor network, the matrix product state (MPS), has generally lead to monotonic…

Machine Learning · Computer Science 2022-08-10 Artem Strashko , E. Miles Stoudenmire

Over-parametrization has become a popular technique in deep learning. It is observed that by over-parametrization, a larger neural network needs a fewer training iterations than a smaller one to achieve a certain level of performance --…

Machine Learning · Computer Science 2021-09-29 Jun-Kun Wang , Jacob Abernethy

Recent theoretical works on over-parameterized neural nets have focused on two aspects: optimization and generalization. Many existing works that study optimization and generalization together are based on neural tangent kernel and require…

Machine Learning · Computer Science 2021-04-27 Shiyu Liang , Ruoyu Sun , R. Srikant

In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal…

Machine Learning · Computer Science 2024-02-21 Elena Agliari , Francesco Alemanno , Miriam Aquaro , Alberto Fachechi

Recent research in neural networks and machine learning suggests that using many more parameters than strictly required by the initial complexity of a regression problem can result in more accurate or faster-converging models -- contrary to…

Machine Learning · Computer Science 2023-05-18 Arthur Castello B. de Oliveira , Milad Siami , Eduardo D. Sontag

This paper rigorously shows how over-parameterization changes the convergence behaviors of gradient descent (GD) for the matrix sensing problem, where the goal is to recover an unknown low-rank ground-truth matrix from near-isotropic linear…

Machine Learning · Computer Science 2023-11-27 Nuoya Xiong , Lijun Ding , Simon S. Du

The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited…

Machine Learning · Computer Science 2019-10-08 Spencer Frei , Yuan Cao , Quanquan Gu

Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is particularly relevant given the perhaps surprising observation…

Machine Learning · Computer Science 2020-10-26 Brian R. Bartoldson , Ari S. Morcos , Adrian Barbu , Gordon Erlebacher

We study the generalization properties of minimum-norm solutions for three over-parametrized machine learning models including the random feature model, the two-layer neural network model and the residual network model. We proved that for…

Machine Learning · Statistics 2021-01-29 Weinan E , Chao Ma , Lei Wu

While over-parameterization is widely believed to be crucial for the success of optimization for the neural networks, most existing theories on over-parameterization do not fully explain the reason -- they either work in the Neural Tangent…

Machine Learning · Computer Science 2021-07-06 Mo Zhou , Rong Ge , Chi Jin

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

We show that learning can be improved by using loss functions that evolve cyclically during training to emphasize one class at a time. In underparameterized networks, such dynamical loss functions can lead to successful training for…

Machine Learning · Computer Science 2021-06-24 Miguel Ruiz-Garcia , Ge Zhang , Samuel S. Schoenholz , Andrea J. Liu

Despite extensive studies, the underlying reason as to why overparameterized neural networks can generalize remains elusive. Existing theory shows that common stochastic optimizers prefer flatter minimizers of the training loss, and thus a…

Machine Learning · Computer Science 2023-07-25 Kaiyue Wen , Zhiyuan Li , Tengyu Ma
‹ Prev 1 3 4 5 6 7 10 Next ›