English
Related papers

Related papers: Approximating Matrix Functions with Deep Neural Ne…

200 papers

We analyze approximation rates of deep ReLU neural networks for Sobolev-regular functions with respect to weaker Sobolev norms. First, we construct, based on a calculus of ReLU networks, artificial neural networks with ReLU activation…

Functional Analysis · Mathematics 2019-02-22 Ingo Gühring , Gitta Kutyniok , Philipp Petersen

In general, approximating classes of functions defined over high-dimensional input spaces by linear combinations of a fixed set of basis functions or ``features'' is known to be hard. Typically, the worst-case error of the best basis set…

Machine Learning · Computer Science 2025-12-05 Jonathan Baxter , Peter Bartlett

A cumbersome operation in many scientific fields, is inverting large full-rank matrices. In this paper, we propose a coded computing approach for recovering matrix inverse approximations. We first present an approximate matrix inversion…

Information Theory · Computer Science 2022-12-21 Neophytos Charalambides , Mert Pilanci , Alfred Hero

Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of…

Machine Learning · Computer Science 2024-10-02 Jizu Huang , Rukang You , Tao Zhou

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Fast approximations to matrix multiplication have the potential to dramatically reduce the cost of neural network inference. Recent work on approximate matrix multiplication proposed to replace costly multiplications with table-lookups by…

Machine Learning · Computer Science 2022-07-14 Calvin McCarter , Nicholas Dronen

We show that deep networks are better than shallow networks at approximating functions that can be expressed as a composition of functions described by a directed acyclic graph, because the deep networks can be designed to have the same…

Machine Learning · Computer Science 2019-11-26 H. N. Mhaskar , T. Poggio

The computation of a matrix function $f(A)$ is an important task in scientific computing appearing in machine learning, network analysis and the solution of partial differential equations. In this work, we use only matrix-vector products…

Numerical Analysis · Mathematics 2026-03-03 Taejun Park , Yuji Nakatsukasa

Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation functions have been inconsistent and task dependent, and…

Machine Learning · Computer Science 2022-01-25 Garrett Bingham , Risto Miikkulainen

Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions. We prove that at any order, the ENO interpolation procedure can be cast as a deep ReLU neural network. This surprising fact enables…

Numerical Analysis · Mathematics 2020-10-09 Tim De Ryck , Siddhartha Mishra , Deep Ray

Looped Transformers provide advantages in parameter efficiency, computational capabilities, and generalization for reasoning tasks. However, their expressive power regarding function approximation remains underexplored. In this paper, we…

Machine Learning · Computer Science 2025-06-06 Kevin Xu , Issei Sato

Homomorphic encryption is one of the representative solutions to privacy-preserving machine learning (PPML) classification enabling the server to classify private data of clients while guaranteeing privacy. This work focuses on PPML using…

Cryptography and Security · Computer Science 2021-06-15 Junghyun Lee , Eunsang Lee , Joon-Woo Lee , Yongjune Kim , Young-Sik Kim , Jong-Seon No

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

Machine Learning · Computer Science 2019-09-04 Lili Su , Pengkun Yang

This paper investigates whether sequence models can learn to perform numerical algorithms, e.g. gradient descent, on the fundamental problem of least squares. Our goal is to inherit two properties of standard algorithms from numerical…

Machine Learning · Computer Science 2025-03-18 Jerry Liu , Jessica Grogan , Owen Dugan , Ashish Rao , Simran Arora , Atri Rudra , Christopher Ré

We consider a family of deep neural networks consisting of two groups of convolutional layers, a downsampling operator, and a fully connected layer. The network structure depends on two structural parameters which determine the numbers of…

Machine Learning · Computer Science 2021-07-05 Tong Mao , Zhongjie Shi , Ding-Xuan Zhou

Properties of Fisher information matrices of 2-layer neural ReLU networks with random hidden weights are studied. For these networks, it is known that the eigenvalue distribution highly concentrates on several eigenspaces approximately. In…

Machine Learning · Statistics 2026-05-13 Ka Long Keith Ho , Yoshinari Takeishi , Junichi Takeuchi

Neural networks are powerful functions with widespread use, but the theoretical behaviour of these functions is not fully understood. Creating deep neural networks by stacking many layers has achieved exceptional performance in many…

Machine Learning · Computer Science 2024-08-16 Cameron Jakub , Mihai Nica

We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponentially small…

Machine Learning · Computer Science 2026-02-10 Abhigyan Dutta , Itay Safran , Paul Valiant

In many neural models, new features as polynomial functions of existing ones are used to augment representations. Using the natural language inference task as an example, we investigate the use of scaled polynomials of degree 2 and above as…

Computation and Language · Computer Science 2018-03-01 Siddhartha Brahma

We study the approximation properties of shallow neural networks with an activation function which is a power of the rectified linear unit. Specifically, we consider the dependence of the approximation rate on the dimension and the…

Numerical Analysis · Mathematics 2021-12-23 Jonathan W. Siegel , Jinchao Xu