Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2108.08859 · Physical Review Letters

Solving Conformal Field Theories with Artificial Intelligence

Gergely Kántor, Constantinos Papageorgakis A, Vasilis Niarchos B

Published Jan 24, 2022• 34 citations
arXivHTMLPDF

Abstract

In this Letter, we deploy for the first time reinforcement-learning algorithms in the context of the conformal-bootstrap program to obtain numerical solutions of conformal field theories (CFTs). As an illustration, we use a soft actor-critic algorithm and find approximate solutions to the truncated crossing equations of two-dimensional CFTs, successfully identifying well-known theories like the 2D Ising model and the 2D CFT of a compactified scalar. Our methods can perform efficient high-dimensional searches that can be used to study arbitrary (unitary or nonunitary) CFTs in any spacetime dimension.

DOI
10.1103/physrevlett.128.041601

Related papers

Conformal bootstrap with reinforcement learning

Gergely Kántor, Vasilis Niarchos B, Constantinos Papageorgakis A

We introduce the use of reinforcement-learning (RL) techniques to the conformal-bootstrap program.We demonstrate that suitable soft Actor-Critic RL algorithms can perform efficient, relatively cheap highdimensional searches in the space of scaling dimensions and OPE-squared coefficients that produce sensible results for tens of CFT data from a single crossing equation.In this paper we test this approach in well-known 2D CFTs, with particular focus on the Ising and tricritical Ising models and the free compactified boson CFT.We present results of as high as 36-dimensional searches, whose sole input is the expected number of operators per spin in a truncation of the conformal-block decomposition of the crossing equations.Our study of 2D CFTs uses only the global soð2; 2Þ part of the conformal algebra, and our methods are equally applicable to higher-dimensional CFTs.When combined with other, already available, numerical and analytical methods, we expect our approach to yield an exciting new window into the nonperturbative structure of arbitrary (unitary or nonunitary) CFTs.

arXiv:2108.09330•Physical review. D/Physical review. D.•Jan 24, 2022•36 citations

Descending into the modular bootstrap

Nathan Benjamin, A. Liam Fitzpatrick, Wei Li +1 more

A bstract In this paper, we attempt to explore the landscape of two-dimensional conformal field theories (2d CFTs) by efficiently searching for numerical solutions to the modular bootstrap equation using machine-learning-style optimization. The torus partition function of a 2d CFT is fixed by the spectrum of its primary operators and its chiral algebra, which we take to be the Virasoro algebra with c > 1. We translate the requirement that this partition function is modular invariant into a loss function, which we then minimize to identify possible primary spectra. Our approach involves two technical innovations that facilitate finding reliable candidate CFTs. The first is a strategy to estimate the uncertainty associated with truncating the spectrum to the lowest dimension operators. The second is the use of a new singular-value-based optimizer (Sven) that is more effective than gradient descent at navigating the hierarchical structure of the loss landscape. We numerically construct candidate truncated CFT partition functions with central charges between 1 and $$\frac{8}{7}$$ , a range devoid of known examples, and argue that these candidates likely come from a continuous space of modular bootstrap solutions. We also provide evidence for a more stringent constraint on the spectral gap near c = 1 than the existing bound of $${\Delta}_{\text {gap}}\le \frac{c}{6}+\frac{1}{3}$$ .

arXiv:2604.01275•Journal of High Energy Physics•Sep 2, 2026•0 citations

Weizmann lectures on the numerical conformal bootstrap

Shai M. Chester

These lectures were given at the Weizmann Institute in the spring of 2019. They are intended to familiarize students with the nuts and bolts of the numerical bootstrap as efficiently as possible. After a brief review of the basics of conformal field theory in d>2 spacetime dimensions, we discuss how to compute conformal blocks, formulate the crossing equations as a semi-definite programming problem, solve this problem using SDPB on a personal computer, and interpret the results. We include worked examples for all steps, including bounds for 3d CFTs with Z2 or O(N) global symmetries. Each lecture includes a problem set, which culminate in a precise computation of the 3d Ising model critical exponents using the mixed correlator Z2 bootstrap. A Mathematica file is included that transforms crossing equations into the proper input form for SDPB.

arXiv:1907.05147•Physics Reports•Nov 2, 2023•52 citations

Machine learning etudes in conformal field theories

Heng‐Yu Chen, Yang‐Hui He, Shailesh Lal +1 more

We demonstrate that various aspects of Conformal Field Theory are amenable to machine learning. Relatively modest feed-forward neural networks are able to distinguish between scale and conformal invariance of a three-point function and identify a crossing-symmetric four-point function to nearly 100% accuracy. Furthermore, neural networks are also able to identify conformal blocks appearing in a putative CFT four-point function and predict the values of the corresponding operator product expansions (OPE) coefficients. Neural networks also successfully classify primary operators by their quantum numbers under discrete symmetries in the CFT from examining OPE data. We also demonstrate that neural networks are able to learn the available OPE data for scalar correlation function in the 3D Ising model and predict the twists of higher-spin operators that appear in scalar OPE channels by regression.

arXiv:2006.16114•International Journal of Data Science in the Mathematical Sciences•Nov 28, 2022•12 citations

COLD ATOMS AND THE CONFORMAL BOOTSTRAP

Joshua William Squires

Statistical mechanics naturally lends itself to computational algorithms that use random sampling to leverage the law of large numbers. Though these methods have proven invaluable, in many cases yielding solutions to otherwise intractable problems, to an extent they also obscure the underlying physics. The two numerical methods studied in this thesis do not fit this description. The first, the conformal bootstrap, imposes symmetry constraints on the four-point correlation functions of a conformal field theory to restrict the spectrum of allowed scaling dimensions of a theory. A variation of the conformal bootstrap is implemented to treat two important non-unitary CFTs, percolation and the self-avoiding walk. The second involves a formalism which provides an integral equation with a kernel based on the two-body S-matrix. The solution of this integral equation represents a single particle's energy in the presence of interactions with the rest of a cold atom gas. The formalism is applied to Berezinskii-Kosterlitz-Thouless and upper branch phase transitions.

•Jan 1, 2019•0 citations

Decoding conformal field theories: From supervised to unsupervised learning

En-Jui Kuo, Alireza Seif, Rex Lundgren +2 more

We use machine learning to classify rational two-dimensional conformal field theories (CFTs). We first use the energy spectra of these minimal models to train a supervised learning algorithm. In contrast to conventional methods that are typically qualitative and also involve system size scaling, our method quantifies the similarity of the spectrum of a system at a fixed size to candidate CFTs. Such an approach allows us to correctly predict the nature and the value of critical points of several strongly correlated spin models using only their energy spectra. Our results are also relevant for the ground-state entanglement Hamiltonian of certain topological phases of matter, described by CFTs. Remarkably, we achieve high prediction accuracy by only using the lowest few R\'eyni entropies as the input. Finally, using autoencoders, an unsupervised learning algorithm, we find a hidden variable that has a direct correlation with the central charge and discuss prospects for using machine learning to investigate other conformal field theories, including higher-dimensional ones.

Physical Review Research•Oct 17, 2022•5 citations
In this Letter, we deploy for the first time reinforcement-learning algorithms in the context of the conformal-bootstrap program to obtain numerical solutions of conformal field theories (CFTs). As an illustration, we use a soft actor-critic algorithm and find approximate solutions to the truncated crossing equations of two-dimensional CFTs, successfully identifying well-known theories like the 2D Ising model and the 2D CFT of a compactified scalar. Our methods can perform efficient high-dimensional searches that can be used to study arbitrary (unitary or nonunitary) CFTs in any spacetime dimension.
We introduce the use of reinforcement-learning (RL) techniques to the conformal-bootstrap program.We demonstrate that suitable soft Actor-Critic RL algorithms can perform efficient, relatively cheap highdimensional searches in the space of scaling dimensions and OPE-squared coefficients that produce sensible results for tens of CFT data from a single crossing equation.In this paper we test this approach in well-known 2D CFTs, with particular focus on the Ising and tricritical Ising models and the free compactified boson CFT.We present results of as high as 36-dimensional searches, whose sole input is the expected number of operators per spin in a truncation of the conformal-block decomposition of the crossing equations.Our study of 2D CFTs uses only the global soð2; 2Þ part of the conformal algebra, and our methods are equally applicable to higher-dimensional CFTs.When combined with other, already available, numerical and analytical methods, we expect our approach to yield an exciting new window into the nonperturbative structure of arbitrary (unitary or nonunitary) CFTs.
A bstract In this paper, we attempt to explore the landscape of two-dimensional conformal field theories (2d CFTs) by efficiently searching for numerical solutions to the modular bootstrap equation using machine-learning-style optimization. The torus partition function of a 2d CFT is fixed by the spectrum of its primary operators and its chiral algebra, which we take to be the Virasoro algebra with c > 1. We translate the requirement that this partition function is modular invariant into a loss function, which we then minimize to identify possible primary spectra. Our approach involves two technical innovations that facilitate finding reliable candidate CFTs. The first is a strategy to estimate the uncertainty associated with truncating the spectrum to the lowest dimension operators. The second is the use of a new singular-value-based optimizer (Sven) that is more effective than gradient descent at navigating the hierarchical structure of the loss landscape. We numerically construct candidate truncated CFT partition functions with central charges between 1 and 87\frac{8}{7}78​ , a range devoid of known examples, and argue that these candidates likely come from a continuous space of modular bootstrap solutions. We also provide evidence for a more stringent constraint on the spectral gap near c = 1 than the existing bound of Δgap≤c6+13{\Delta}_{\text {gap}}\le \frac{c}{6}+\frac{1}{3}Δgap​≤6c​+31​ .
These lectures were given at the Weizmann Institute in the spring of 2019. They are intended to familiarize students with the nuts and bolts of the numerical bootstrap as efficiently as possible. After a brief review of the basics of conformal field theory in d>2 spacetime dimensions, we discuss how to compute conformal blocks, formulate the crossing equations as a semi-definite programming problem, solve this problem using SDPB on a personal computer, and interpret the results. We include worked examples for all steps, including bounds for 3d CFTs with Z2 or O(N) global symmetries. Each lecture includes a problem set, which culminate in a precise computation of the 3d Ising model critical exponents using the mixed correlator Z2 bootstrap. A Mathematica file is included that transforms crossing equations into the proper input form for SDPB.
We demonstrate that various aspects of Conformal Field Theory are amenable to machine learning. Relatively modest feed-forward neural networks are able to distinguish between scale and conformal invariance of a three-point function and identify a crossing-symmetric four-point function to nearly 100% accuracy. Furthermore, neural networks are also able to identify conformal blocks appearing in a putative CFT four-point function and predict the values of the corresponding operator product expansions (OPE) coefficients. Neural networks also successfully classify primary operators by their quantum numbers under discrete symmetries in the CFT from examining OPE data. We also demonstrate that neural networks are able to learn the available OPE data for scalar correlation function in the 3D Ising model and predict the twists of higher-spin operators that appear in scalar OPE channels by regression.
Statistical mechanics naturally lends itself to computational algorithms that use random sampling to leverage the law of large numbers. Though these methods have proven invaluable, in many cases yielding solutions to otherwise intractable problems, to an extent they also obscure the underlying physics. The two numerical methods studied in this thesis do not fit this description. The first, the conformal bootstrap, imposes symmetry constraints on the four-point correlation functions of a conformal field theory to restrict the spectrum of allowed scaling dimensions of a theory. A variation of the conformal bootstrap is implemented to treat two important non-unitary CFTs, percolation and the self-avoiding walk. The second involves a formalism which provides an integral equation with a kernel based on the two-body S-matrix. The solution of this integral equation represents a single particle's energy in the presence of interactions with the rest of a cold atom gas. The formalism is applied to Berezinskii-Kosterlitz-Thouless and upper branch phase transitions.
We use machine learning to classify rational two-dimensional conformal field theories (CFTs). We first use the energy spectra of these minimal models to train a supervised learning algorithm. In contrast to conventional methods that are typically qualitative and also involve system size scaling, our method quantifies the similarity of the spectrum of a system at a fixed size to candidate CFTs. Such an approach allows us to correctly predict the nature and the value of critical points of several strongly correlated spin models using only their energy spectra. Our results are also relevant for the ground-state entanglement Hamiltonian of certain topological phases of matter, described by CFTs. Remarkably, we achieve high prediction accuracy by only using the lowest few R\'eyni entropies as the input. Finally, using autoencoders, an unsupervised learning algorithm, we find a hidden variable that has a direct correlation with the central charge and discuss prospects for using machine learning to investigate other conformal field theories, including higher-dimensional ones.