James Halverson

James Halverson

Auto-generated profile, based on publicly available information

James Halverson

Northeastern University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 April 2021 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
PDF file
JHJames Halverson
James Halverson
Anindita MaitiAnindita Maiti
Anindita Maiti
KSKeegan Stoner
Keegan Stoner
We propose a theoretical understanding of neural networks in terms of Wilsonian effective field theory. The correspondence relies on the fact that many asymptotic neural networks are drawn from Gaussian processes (GPs), the analog of non-interacting field theories. Moving away from the asymptotic limit yields a non-Gaussian process (NGP) and corresponds to turning on particle interactions, allowing for the computation of correlation functions of neural network outputs with Feynman diagrams. Minimal NGP likelihoods are determined by the most relevant non-Gaussian terms, according to the flow in their coefficients induced by the Wilsonian renormalization group. This yields a direct connection between overparameterization and simplicity of neural network likelihoods. Whether the coefficients are constants or functions may be understood in terms of GP limit symmetries, as expected from ’t Hooft’s technical naturalness. General theoretical calculations are matched to neural network experiments in the simplest class of models allowing the correspondence. Our formalism is valid for any of the many architectures that becomes a GP in an asymptotic limit, a property preserved under certain types of training.

3 June 2019 in Journal of High Energy Physics
Verified
Journal Article
Open access
PDF file
JHJames Halverson
James Halverson
BNBrent Nelson
Brent Nelson
FRFabian Ruehle
Fabian Ruehle
We propose deep reinforcement learning as a model-free method for exploring the landscape of string vacua. As a concrete application, we utilize an artificial intelligence agent known as an asynchronous advantage actor-critic to explore type IIA compactifications with intersecting D6-branes. As different string background configurations are explored by changing D6-brane configurations, the agent receives rewards and punishments related to string consistency conditions and proximity to Standard Model vacua. These are in turn utilized to update the agent’s policy and value neural networks to improve its behavior. By reinforcement learning, the agent’s performance in both tasks is significantly improved, and for some tasks it finds a factor of $$ \mathcal{O}(200) $$ O 200 more solutions than a random walker. In one case, we demonstrate that the agent learns a human-derived strategy for finding consistent string models. In another case, where no human-derived strategy exists, the agent learns a genuinely new strategy that achieves the same goal twice as efficiently per unit time. Our results demonstrate that the agent learns to solve various string theory consistency conditions simultaneously, which are phrased in terms of non-linear, coupled Diophantine equations.

18 May 2021 in Journal of High Energy Physics
Verified
Journal Article
Open access
PDF file
JHJames Halverson
James Halverson
CLCody Long
Cody Long
Anindita MaitiAnindita Maiti
Anindita Maiti
BNBrent Nelson
Brent Nelson
GSGustavo Salinas
Gustavo Salinas
Dark Yang-Mills sectors, which are ubiquitous in the string landscape, may be reheated above their critical temperature and subsequently go through a confining first-order phase transition that produces stochastic gravitational waves in the early universe. Taking into account constraints from lattice and from Yang-Mills (center and Weyl) symmetries, we use a phenomenological model to construct an effective potential of the semi quark-gluon plasma phase, from which we compute the gravitational wave signal produced during confinement for numerous gauge groups. The signal is maximized when the dark sector dominates the energy density of the universe at the time of the phase transition. In that case, we find that it is within reach of the next-to-next generation of experiments (BBO, DECIGO) for a range of dark confinement scales near the weak scale.

21 April 2021 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
PDF file
SGSergei Gukov
Sergei Gukov
JHJames Halverson
James Halverson
FRFabian Ruehle
Fabian Ruehle
PSPiotr Sułkowski
Piotr Sułkowski
We introduce natural language processing into the study of knot theory, as made natural by the braid word representation of knots. We study the UNKNOT problem of determining whether or not a given knot is the unknot. After describing an algorithm to randomly generate N-crossing braids and their knot closures and discussing the induced prior on the distribution of knots, we apply binary classification to the UNKNOT decision problem. We find that the Reformer and shared-QK Transformer network architectures outperform fully-connected networks, though all perform at ≳ 95% accuracy. Perhaps surprisingly, we find that accuracy increases with the length of the braid word, and that the networks learn a direct correlation between the confidence of their predictions and the degree of the Jones polynomial. Finally, we utilize reinforcement learning (RL) to find sequences of Markov moves and braid relations that simplify knots and can identify unknots by explicitly giving the sequence of unknotting actions. Trust region policy optimization (TRPO) performs consistently well, reducing ≳ 80% of the unknots with up to 96 crossings we tested to the empty braid word, and thoroughly outperformed other RL algorithms and random walkers. Studying these actions, we find that braid relations are more useful in simplifying to the unknot than one of the Markov moves.

13 September 2018 in Journal of High Energy Physics
Verified
Journal Article
Open access
PDF file
ABAndreas P. Braun
Andreas P. Braun
MZMichele Del Zotto
Michele Del Zotto
JHJames Halverson
James Halverson
MLMagdalena Larfors
Magdalena Larfors
DMDavid R. Morrison
David R. Morrison
SSSakura Schäfer-Nameki
Sakura Schäfer-Nameki
We consider the non-perturbative superpotential for a class of four-dimensional $$ \mathcal{N}=1 $$ N = 1 vacua obtained from M-theory on seven-manifolds with holonomy G 2. The class of G 2-holonomy manifolds we consider are so-called twisted connected sum (TCS) constructions, which have the topology of a K3-fibration over S 3. We show that the non-perturbative superpotential of M-theory on a class of TCS geometries receives infinitely many inequivalent M2-instanton contributions from infinitely many three-spheres, which we conjecture are supersymmetric (and thus associative) cycles. The rationale for our construction is provided by the duality chain of [1], which relates M-theory on TCS G 2-manifolds to E 8 × E 8 heterotic backgrounds on the Schoen Calabi-Yau threefold, as well as to F-theory on a K3-fibered Calabi-Yau fourfold. The latter are known to have an infinite number of instanton corrections to the superpotential and it is these contributions that we trace through the duality chain back to the G 2-compactification.

9 January 2024 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
PDF file
MDMehmet Demirtas
Mehmet Demirtas
JHJames Halverson
James Halverson
Anindita MaitiAnindita Maiti
Anindita Maiti
MSMatthew D. Schwartz
Matthew D. Schwartz
KSKeegan Stoner
Keegan Stoner
Both the path integral measure in field theory (FT) and ensembles of neural networks (NN) describe distributions over functions. When the central limit theorem can be applied in the infinite-width (infinite-N) limit, the ensemble of networks corresponds to a free FT. Although an expansion in 1/N corresponds to interactions in the FT, others, such as in a small breaking of the statistical independence of network parameters, can also lead to interacting theories. These other expansions can be advantageous over the 1/N -expansion, for example by improved behavior with respect to the universal approximation theorem. Given the connected correlators of a FT, one can systematically reconstruct the action order-by-order in the expansion parameter, using a new Feynman diagram prescription whose vertices are the connected correlators. This method is motivated by the Edgeworth expansion and allows one to derive actions for NN FT. Conversely, the correspondence allows one to engineer architectures realizing a given FT by representing action deformations as deformations of NN parameter densities. As an example,φ4theory is realized as an infinite-NNN FT.