English
Related papers

Related papers: Geometry and Optimization of Shallow Polynomial Ne…

200 papers

We study the approximation gap between the dynamics of a polynomial-width neural network and its infinite-width counterpart, both trained using projected gradient descent in the mean-field scaling regime. We demonstrate how to tightly bound…

Machine Learning · Statistics 2025-09-25 Margalit Glasgow , Denny Wu , Joan Bruna

This paper investigates the state estimation problem for a class of complex networks, in which the dynamics of each node is subject to Gaussian noise, system uncertainties and nonlinearities. Based on a regularized least-squares approach,…

Systems and Control · Electrical Eng. & Systems 2021-03-16 Peihu Duan , Qishao Wang , Zhisheng Duan , Guanrong Chen

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

Machine Learning · Statistics 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of…

Disordered Systems and Neural Networks · Physics 2017-09-13 Henry W. Lin , Max Tegmark , David Rolnick

Compactly representing and efficently applying linear operators are fundamental ingredients in tensor network methods for simulating quantum many-body problems and solving high-dimensional problems in scientific computing. In this work, we…

Numerical Analysis · Mathematics 2024-05-17 Gianluca Ceruti , Daniel Kressner , Dominik Sulz

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer $l$, the number…

Machine Learning · Computer Science 2020-06-30 Yuandong Tian

Motivated by distributed statistical learning over uncertain communication networks, we study distributed stochastic optimization by networked nodes to cooperatively minimize a sum of convex cost functions. The network is modeled by a…

Systems and Control · Electrical Eng. & Systems 2025-01-03 Yan Chen , Alexander L. Fradkov , Keli Fu , Xiaozheng Fu , Tao Li

Theoretical neuroscientists often try to understand how the structure of a neural network relates to its function by focusing on structural features that would either follow from optimization or occur consistently across possible…

Neurons and Cognition · Quantitative Biology 2025-06-16 Tirthabir Biswas , Tianzhi Lambus Li , Selimzhan Chalyshkan , Fumi Kubo , James E. Fitzgerald

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence…

Machine Learning · Statistics 2026-03-06 Eloy Mosig , Andrea Agazzi , Dario Trevisan

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

Low rank tensor decompositions are a powerful tool for learning generative models, and uniqueness results give them a significant advantage over matrix decomposition methods. However, tensors pose significant algorithmic challenges and…

Data Structures and Algorithms · Computer Science 2014-01-21 Aditya Bhaskara , Moses Charikar , Ankur Moitra , Aravindan Vijayaraghavan

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

We study the optimization and sample complexity of gradient-based training of a two-layer neural network with quadratic activation function in the high-dimensional regime, where the data is generated as $f_*(\boldsymbol{x}) \propto…

Machine Learning · Statistics 2026-01-01 Gérard Ben Arous , Murat A. Erdogdu , Nuri Mert Vural , Denny Wu

We discuss a possibility that the entire universe on its most fundamental level is a neural network. We identify two different types of dynamical degrees of freedom: "trainable" variables (e.g. bias vector or weight matrix) and "hidden"…

General Physics · Physics 2020-12-02 Vitaly Vanchurin

We study polynomial optimization problems whose objective has a composition or tensor train structure. These polynomials can be evaluated as a sequence of maps, giving rise to intermediate variables (``states'') of dimension lower than the…

Optimization and Control · Mathematics 2026-04-21 Llorenç Balada Gaggioli , Didier Henrion , Milan Korda

Here we utilize a low-rank tensor model (LTM) as a function approximator, combined with the gradient descent method, to solve eigenvalue problems including the Laplacian operator and the harmonic oscillator. Experimental results show the…

Machine Learning · Computer Science 2023-02-02 Jun Hu , Pengzhan Jin

High-dimensional sparse data present computational and statistical challenges for supervised learning. We propose compact linear sketches for reducing the dimensionality of the input, followed by a single layer neural network. We show that…

Machine Learning · Computer Science 2016-04-21 Amit Daniely , Nevena Lazic , Yoram Singer , Kunal Talwar

We explore the probabilistic partition of unity network (PPOU-Net) model in the context of high-dimensional regression problems and propose a general framework focusing on adaptive dimensionality reduction. With the proposed framework, the…

Machine Learning · Computer Science 2023-06-13 Tiffany Fan , Nathaniel Trask , Marta D'Elia , Eric Darve

Recent work has highlighted a surprising alignment between gradients and the top eigenspace of the Hessian -- termed the Dominant subspace -- during neural network training. Concurrently, there has been growing interest in the distinct…

Machine Learning · Computer Science 2025-05-20 Daniyar Zakarin , Sidak Pal Singh

Tensor networks are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to supervised…

Machine Learning · Statistics 2017-05-22 E. Miles Stoudenmire , David J. Schwab