English
Related papers

Related papers: How Two-Layer Neural Networks Learn, One (Giant) S…

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

Motivated by the observation that humans can learn patterns from two given images at one time, we propose a dual pattern learning network architecture in this paper. Unlike conventional networks, the proposed architecture has two input…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Haimin Zhang , Min Xu

Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DNNs by selecting appropriate norms for different layers and…

Machine Learning · Computer Science 2026-02-04 Jie Hao , Xiaochuan Gong , Jie Xu , Zhengdao Wang , Mingrui Liu

The typical training of neural networks using large stepsize gradient descent (GD) under the logistic loss often involves two distinct phases, where the empirical risk oscillates in the first phase but decreases monotonically in the second…

Machine Learning · Statistics 2024-06-28 Yuhang Cai , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are updated. General initialization schemes as well as general…

Machine Learning · Computer Science 2020-02-27 Weinan E , Chao Ma , Lei Wu

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we…

Machine Learning · Computer Science 2019-10-28 Cong Fang , Hanze Dong , Tong Zhang

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural…

Machine Learning · Statistics 2022-03-28 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Several recent works have shown separation results between deep neural networks, and hypothesis classes with inferior approximation capacity such as shallow networks or kernel classes. On the other hand, the fact that deep networks can…

Machine Learning · Computer Science 2021-07-20 Eran Malach , Gilad Yehudai , Shai Shalev-Shwartz , Ohad Shamir

In this manuscript, we study the learning of deep attention neural networks, defined as the composition of multiple self-attention layers, with tied and low-rank weights. We first establish a mapping of such models to sequence multi-index…

Machine Learning · Computer Science 2025-11-13 Emanuele Troiani , Hugo Cui , Yatin Dandi , Florent Krzakala , Lenka Zdeborová

Significant theoretical work has established that in specific regimes, neural networks trained by gradient descent behave like kernel methods. However, in practice, it is known that neural networks strongly outperform their associated…

Machine Learning · Computer Science 2022-07-01 Alex Damian , Jason D. Lee , Mahdi Soltanolkotabi

Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with…

Machine Learning · Computer Science 2025-02-24 Yizhou Xu , Liu Ziyin

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

Although the neural network (NN) technique plays an important role in machine learning, understanding the mechanism of NN models and the transparency of deep learning still require more basic research. In this study, we propose a novel…

Machine Learning · Computer Science 2023-11-10 Shuyue Guan , Murray Loew

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on a variety of regularization and pruning techniques to…

Computer Vision and Pattern Recognition · Computer Science 2017-10-23 Martin Mundt , Tobias Weis , Kishore Konda , Visvanathan Ramesh