arXiv Machine Learning June 4, 2026 By Andrew Gracyk

Shortcomings and capacities of real-constrained neural networks in complex spaces

Read the original on arXiv Machine Learning →

arXiv:2606. 04390v1 Announce Type: new Abstract: We find the asymptotic ratio between the storage capacities when enforcing real pre-activations in a complex hypothesis class as opposed to complex ones in the same class.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 7

Shallow neural network approximation in mixed Sobolev spaces

arXiv:2609. 05263v1 Announce Type: cross Abstract: We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with $n$ neurons and general activation functions.

By Yuwen Li, Guozhi Zhang

arXiv Machine Learning

Aug 21

K\"ahler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifold

arXiv:2608. 19584v1 Announce Type: new Abstract: We study landscapes for complex-parameterized networks.

By Andrew Gracyk

arXiv AI

Oct 15

Lifting Finite-Sample Gaussian Approximation of Wide Neural Networks to Functional Convergence

arXiv:2610.18166v1 Announce Type: cross Abstract: Randomly initialised neural networks of width $m$ converge to Gaussian processes as $m \to \infty$, with two types of quantitative bounds characteris...

By Luis Wiederhold, Nil Ayday, Debarghya Ghoshdastidar

arXiv Machine Learning

Jul 14

Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width

arXiv:2607. 10589v1 Announce Type: cross Abstract: In contrast to most studies on neural network approximation theory that characterize results through a single parameter, such as the total number of network parameters, \cite{shen2020deep} pioneered the characterization of approximation rates as a joint function of the width parameter $N$ and the depth parameter $L$, thereby granting greater architectural flexibility.

By Yanming Lai, Defeng Sun, Yang Wang

arXiv Machine Learning

Jul 7

A short tour of operator learning theory: Convergence rates, statistical limits, and open questions

arXiv:2603. 00819v2 Announce Type: replace-cross Abstract: This paper surveys recent developments at the intersection of operator learning, statistical learning theory, and approximation theory.

By Simone Brugiapaglia, Nicola Rares Franco, Nicholas H. Nelsen

arXiv Machine Learning

Jul 21

Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space

arXiv:2106. 04770v2 Announce Type: replace Abstract: We study parameter nonuniqueness in continuous-width depth-two fully connected neural networks.

By Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

One email a morning, machine-written

Related stories

Shallow neural network approximation in mixed Sobolev spaces

K\"ahler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifold

Lifting Finite-Sample Gaussian Approximation of Wide Neural Networks to Functional Convergence

Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width

A short tour of operator learning theory: Convergence rates, statistical limits, and open questions

Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space