English
Related papers

Related papers: Optimization and Generalization of Shallow Neural …

200 papers

We study the training dynamics of a shallow neural network with quadratic activation functions and quadratic cost in a teacher-student setup. In line with previous works on the same neural architecture, the optimization is performed…

Optimization and Control · Mathematics 2023-11-08 Simon Martin , Francis Bach , Giulio Biroli

Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-student setting, where a network is trained on data generated…

Disordered Systems and Neural Networks · Physics 2026-03-26 Rodrigo Pérez Ortiz , Gibbs Nwemadji , Jean Barbier , Federica Gerace , Alessandro Ingrosso , Clarissa Lauditi , Enrico M. Malatesta

We consider the teacher-student setting of learning shallow neural networks with quadratic activations and planted weight matrix $W^*\in\mathbb{R}^{m\times d}$, where $m$ is the width of the hidden layer and $d\le m$ is the data dimension.…

Machine Learning · Statistics 2020-07-13 David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

We study shallow neural networks with monomial activations and output dimension one. The function space for these models can be identified with a set of symmetric tensors with bounded rank. We describe general features of these networks,…

Machine Learning · Computer Science 2025-12-18 Yossi Arjevani , Joan Bruna , Joe Kileel , Elzbieta Polak , Matthew Trager

Despite their practical success, a theoretical understanding of the loss landscape of neural networks has proven challenging due to the high-dimensional, non-convex, and highly nonlinear structure of such models. In this paper, we…

Machine Learning · Computer Science 2020-07-21 Abbas Kazemipour , Brett W. Larsen , Shaul Druckmann

We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \ge \sqrt{2n}$,…

Machine Learning · Computer Science 2018-06-18 Simon S. Du , Jason D. Lee

In this paper we study the problem of learning a shallow artificial neural network that best fits a training data set. We study this problem in the over-parameterized regime where the number of observations are fewer than the number of…

Machine Learning · Computer Science 2022-08-25 Mahdi Soltanolkotabi , Adel Javanmard , Jason D. Lee

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

We study the high-dimensional training dynamics of a shallow neural network with quadratic activation in a teacher-student setup. We focus on the extensive-width regime, where the teacher and student network widths scale proportionally with…

Optimization and Control · Mathematics 2026-01-16 Simon Martin , Giulio Biroli , Francis Bach

We prove that if an activation function satisfies some mild conditions and number of neurons in a two-layered fully connected neural network with this activation function is beyond a certain threshold, then gradient descent on quadratic…

Optimization and Control · Mathematics 2019-11-14 Biswarup Das , Eugene. A. Golikov

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

While the optimization problem behind deep neural networks is highly non-convex, it is frequently observed in practice that training deep networks seems possible without getting stuck in suboptimal points. It has been argued that this is…

Machine Learning · Computer Science 2017-06-14 Quynh Nguyen , Matthias Hein

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

Modern neural networks are often quite wide, causing large memory and computation costs. It is thus of great interest to train a narrower network. However, training narrow neural nets remains a challenging task. We ask two theoretical…

Machine Learning · Computer Science 2022-10-24 Jiawei Zhang , Yushun Zhang , Mingyi Hong , Ruoyu Sun , Zhi-Quan Luo

We examine the squared error loss landscape of shallow linear neural networks. We show---with significantly milder assumptions than previous works---that the corresponding optimization problems have benign geometric properties: there are no…

Machine Learning · Computer Science 2018-11-06 Zhihui Zhu , Daniel Soudry , Yonina C. Eldar , Michael B. Wakin

We analyze the one-pass stochastic gradient descent dynamics of a two-layer neural network with quadratic activations in a teacher--student framework. In the high-dimensional regime, where the input dimension $N$ and the number of samples…

Disordered Systems and Neural Networks · Physics 2026-04-06 Dario Bocchi , Theotime Regimbeau , Carlo Lucibello , Luca Saglietti , Chiara Cammarota

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

Recent numerical experiments have demonstrated that the choice of optimization geometry used during training can impact generalization performance when learning expressive nonlinear model classes such as deep neural networks. These…

Machine Learning · Computer Science 2022-04-25 Nicholas M. Boffi , Stephen Tu , Jean-Jacques E. Slotine

This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose…

Machine Learning · Computer Science 2025-07-23 Zhihan Zeng , Yiqi Gu
‹ Prev 1 2 3 10 Next ›