533 citations · 558 across the 14 of their papers we have counts for
16 papers
Spinning Conformal Correlators from Neural Networks
Manas Dogra, James Halverson, Joydeep Naskar
We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on scalar confo…
Pre-Strings Lectures on Artificial Intelligence
James Halverson
These notes are based on six lectures given over three days at the Pre-Strings 2026 school in Shanghai. Day 1 develops neural network essentials, organized around the expressivity,…
Naturalness and Fisher Information
James Halverson, Thomas R. Harvey, Michael Nee
Fine-tuning and naturalness, the sensitivity of low-energy observables to small changes in the fundamental parameters of a theory, are cornerstones of physics beyond the Standard M…
Universality of Neural Network Field Theory
Christian Ferko, James Halverson, Aaron Mutchler
We prove that any quantum field theory, or more generally any probability distribution over tempered distributions in , admits a neural network description with a cou…
String Theory from Infinite Width Neural Networks
Samuel Frank, James Halverson
We realize bosonic string theory with ensembles of infinite width neural networks. The string tension is tuned by the variance of the output weights. The construction provides a ne…
F-theory Axiverse
Sebastian Vander Ploeg Fallon, James Halverson, Liam McAllister +1
We compute the couplings of Ramond-Ramond four-form axions in three ensembles of F-theory compactifications, with up to 181,200 axions. We work in the stretched Kähler cone, where…
Fermions and Supersymmetry in Neural Network Field Theories
Samuel Frank, James Halverson, Anindita Maiti +1
We introduce fermionic neural network field theories via Grassmann-valued neural networks. Free theories are obtained by a generalization of the Central Limit Theorem to Grassmann…
Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks
Thomas R. Harvey, Fabian Ruehle, Kit Fraser-Taliente +1
We present a novel approach to symbolic regression using vision-capable large language models (LLMs) and the ideas behind Google DeepMind's Funsearch. The LLM is given a plot of a…
Learning Topological Invariance
James Halverson, Fabian Ruehle
Two geometric spaces are in the same topological class if they are related by certain geometric deformations. We propose machine learning methods that automate learning of topologi…
Quantum Mechanics and Neural Networks
Christian Ferko, James Halverson
We demonstrate that any Euclidean-time quantum mechanical theory may be represented as a neural network, ensured by the Kosambi-Karhunen-Loève theorem, mean-square path continuity,…
Conformal Fields from Neural Networks
James Halverson, Joydeep Naskar, Jiahua Tian
We use the embedding formalism to construct conformal fields in dimensions, by restricting Lorentz-invariant ensembles of homogeneous neural networks in dimensions to t…
On the Generality and Persistence of Cosmological Stasis
James Halverson, Sneh Pandya
Hierarchical decays of matter species to radiation may balance against Hubble expansion to yield stasis, a new phase of cosmological evolution with constant matter and radiatio…
TASI Lectures on Physics for Machine Learning
Jim Halverson
These notes are based on lectures I gave at TASI 2024 on Physics for Machine Learning. The focus is on neural network theory, organized according to network expressivity, statistic…
KAN: Kolmogorov-Arnold Networks
Ziming Liu, Yixuan Wang, Sachin Vaidya +5
Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have…
Rigor with Machine Learning from Field Theory to the Poincaré Conjecture
Sergei Gukov, James Halverson, Fabian Ruehle
Machine learning techniques are increasingly powerful, leading to many breakthroughs in the natural sciences, but they are often stochastic, error-prone, and blackbox. How, then, s…
Metric Flows with Neural Networks
James Halverson, Fabian Ruehle
We develop a general theory of flows in the space of Riemannian metrics induced by neural network gradient descent. This is motivated in part by recent advances in approximating Ca…