betaFeedback

WorksPhysics and Astronomy

Learning from Duality in Neural Network Field Theories

Abstract

We develop neural realizations of positive-level Wess-Zumino-Witten models using bosonic Wakimoto and fermionic Fourier-Berezin fields. Level-rank duality connects the charged sectors of the fermionic construction, where explicit neural observables recover conformal block data and enable the transfer of information about unknown correlators between paired theories. We also show that distinct neural presentations of the same continuum current algebra exhibit different finite-width behavior, with approximation accuracy depending on architecture, regulator, and parameter distribution. These results connect the exact mathematical structure of conformal field theory with the expressive and computational properties of neural field theories.

Introduction

Duality is a central organizing principle in theoretical and mathematical physics. A suitable duality frame can simplify a calculation by reorganizing the degrees of freedom, symmetries or couplings used to describe a theory [1, 2]. At the interface of physics and machine learning such a non-trivial relation in the space of field theories poses a challenge: if two neural architectures realize (quantum) field-theoretic structures related by an exact duality, what does that relation tell us about their finite approximations, computational costs and learning behavior?

Neural Network Field Theory (NNFT) provides a setting for investigating these questions. It associates field-theoretic correlation functions with expectations over ensembles of neural parameters. Appropriate choices of architecture and parameter law can reproduce free-field and conformal-field-theory kernels in a regulated infinite-width limit [3, 4, 5, 6]. However, a limiting covariance is not a complete description of the finite ensemble: higher connected moments, shared-parameter correlations, regulator dependence and the cost of evaluating composite readouts can all depend on how the same kernel is realized [7, 8, 9, 10, 11]. This provides a particularly sharp setting for studying duality. An exact relation between selected continuum observables supplies a fixed physical reference, while the underlying neural implementations can still be varied and compared. Throughout this work, neural feature width, regulator removal, finite operator-mode rank and statistical estimation are treated as distinct operations.

Symmetry-based machine learning often builds group actions into neural features, for example through equivariant architectures, Lie-algebra-valued layers or learned symmetry generators [12, 13, 14, 15, 16, 17]. Our question concerns the operator algebra generated by composite neural observables. Its affine level, normal ordering and descendant states require information beyond the transformation of features under a finite-dimensional group. We calculate these structures from specified neural parameter laws and then examine the finite-ensemble corrections.

We study level–rank duality of Wess–Zumino–Witten (WZW) current algebras as a controlled example. Our central question is which features of the neural realizations are constrained by exact algebraic data and which depend on the finite presentations. WZW models are interacting two-dimensional conformal field theories that have applications in string theory, representation theory and three-dimensional topological field theory [18, 19, 20, 21]. Their holomorphic currents generate affine Kac–Moody algebras g^k\widehat{\mathfrak{g}}_k, and the Sugawara construction produces the corresponding stress tensor [22, 23]. At positive integral level, the integrable highest-weight sectors and fusion rules are controlled by the affine symmetry; chiral correlation functions decompose into conformal blocks constrained by current Ward identities and Knizhnik–Zamolodchikov (KZ) equations [23, 24]. In this setting, current operator product expansions (OPEs), central charges, representation branching and block transport provide different, independently checkable levels of agreement.

Level–rank duality gives a precise relation between two such current algebras. For su^(N)K\widehat{\mathfrak{su}}(N)_K and su^(K)N\widehat{\mathfrak{su}}(K)_N, integrable sectors are paired through Young-diagram transposition together with identifications of appropriate charges, currents, fusion data and spaces of conformal blocks [25, 26, 27, 28]. The free-fermion conformal embedding makes the shared structure explicit:

su^(N)K⊕su^(K)N⊕u^(1)NK⊂u^(NK)1.(1)\widehat{\mathfrak{su}}(N)_{K} \oplus\widehat{\mathfrak{su}}(K)_{N} \oplus\widehat{\mathfrak{u}}(1)_{NK} \subset\widehat{\mathfrak{u}}(NK)_{1}. \tag*{(1)}

The two non-Abelian current algebras act on the row and column indices of an N×KN \times K array of complex fermions, while the additional number-current sector accounts for their common charged parent [25, 27]. This is a correspondence between specified chiral structures, not an equivalence of the complete su(N)K\mathfrak{su}(N)_{K} and su(K)N\mathfrak{su}(K)_{N} WZW theories: their central charges generally differ, and paired conformal blocks need not be equal as functions. Nor does the embedding identify the parameters or finite approximation schemes of the two neural current readouts.

To study level–rank duality in NNFT, we construct affine currents from composite observables of regulated neural free fields. The neural architectures and their parameter laws determine the elementary correlations, while normal ordering and the associated operator constructions determine the current algebras. We evaluate composite correlators at finite width and fixed regulator, and then take the Gaussian limit before removing the regulator. This procedure allows us to study finite-width effects while retaining a well-defined continuum theory.

We develop two complementary constructions of positive-level affine currents. The bosonic construction combines neural scalar fields and commuting first-order βγ\beta\gamma fields through the nonlinear and derivative terms of the Wakimoto construction [29, 30]. The fermionic construction uses Fourier–Berezin fields whose regulated contractions approach the Cauchy kernel. Bilinears of these fields generate commuting su^(N)K\widehat{\mathfrak{su}}(N)_{K} and su^(K)N\widehat{\mathfrak{su}}(K)_{N} current algebras, with positive levels determined by the flavor multiplicities. Both constructions recover the prescribed affine structures in the continuum limit and allow finite-width corrections to be calculated from the underlying neural ensembles.

The fermionic construction also provides access to charged sectors. Angular projections of the Fourier features, together with a Neveu–Schwarz polarization, lead to the canonical anticommutation relations (CAR) and their Fock-space realization. Exterior powers of the N×KN \times K channel space determine the charged lowest-grade sectors, while negative current modes generate their descendants. For NK=6NK = 6, Grassmann antisymmetry gives the two charge-two channels (3,3)(\mathbf{3},\mathbf{3}) and (1,6)(\mathbf{1},\mathbf{6}), relating the intermediate sectors of SU(2)3SU(2)_{3} and SU(3)2SU(3)_{2}. Using the corresponding Ward identities and sewing data, we reconstruct their descendant expansions and find agreement with independent WZW calculations through the tested grades.

We next examine how different neural constructions approach the same continuum theory. A spectral-tilt parameter changes the distribution of sampled frequencies while preserving the limiting elementary correlations. The finite-width correlators admit inverse-width expansions whose coefficients depend on the spectral distribution, regulator and observable. We compare current, stress-tensor and higher-point correlations in direct SU(N)KSU(N)_{K} constructions and their SU(NK)1/SU(K)NSU(NK)_{1}/SU(K)_{N} coset counterparts. The preferred spectral distribution varies with the observable and neural width, while the choice of regulator affects the accuracy relative to the continuum CFT. We also find that changing how parameters are shared across fields can alter the relative accuracy of the direct and coset constructions.

These choices also affect the computational resources. The bosonic SU(6)1SU(6)_1 parent contains more elementary fields and requires more complicated composite observables than the direct SU(2)3SU(2)_3 construction. Their evaluation costs differ according to the correlators being computed and the intermediate calculations that can be reused. We further examine the sensitivity of the correlators to changes in the elementary field amplitudes, and test whether these adjustments improve their agreement with the continuum theory. Finally, we consider sampling uncertainty and the cost of estimating the neural ensemble averages. Together, these calculations describe how the choice of neural construction affects accuracy and computational efficiency.

We also investigate finite-dimensional approximations of the fermionic state spaces. Retaining selected one-particle modes preserves their canonical anticommutation relations, while modifying the composite current algebra and its sewing amplitudes. We compare direct and neural optimization of polarized subspaces against conventional mode truncation. Optimizing the retained modes improves the approximation in two of the five settings studied, with similar performance from the direct and neural methods. The results illustrate how the choice of finite-dimensional subspace affects the approximation of WZW amplitudes.

Finally, we investigate how level–rank duality can be used to transfer information between paired theories. We begin with fusion coefficients, using Kac–Peterson modular data, the Verlinde formula and Young-diagram transposition to relate integrable representations grouped into simple-current orbits [31, 32]. In the two prediction tasks, the correspondence can already be determined from representation-theoretic data, giving the same predictions as a model supplied with the exact matching. We then consider charged correlators whose coefficients must be learned from observations. The level–rank pairing relates the corresponding source and target observables, allowing measurements in one sector to predict the response in the other. We construct these observables explicitly from charged angular polynomials of the finite Fourier–Berezin fields and examine their accuracy against WZW transport. Source-trained predictors recover the paired preparation responses without additional target-preparation measurements.

These results demonstrate how the algebraic relations of WZW models can guide the construction and study of neural field theories. Level–rank duality supplies exact relations between charged sectors, while the finite neural realizations provide a setting for investigating approximation, computational resources and the transfer of learned information.

Summary of contributions. Our main results can be organized into five contributions:

  • Neural realizations of positive-level affine algebras. We construct bosonic Wakimoto and fermionic Fourier–Berezin architectures whose composite observables realize positive-level affine currents and their stress tensors in controlled continuum limits. We derive the limiting current algebras and calculate finite-width corrections directly from the underlying neural parameter laws.

  • Charged sectors and conformal-block transport. Angular projections of the fermionic fields yield the limiting CAR pairing and its Fock-space realization. We identify paired charged sectors and reconstruct their affine descendants, obtaining agreement with independent WZW/KZ calculations through the tested grades. Using physical Ward couplings, we also construct charged angular observables in the finite neural fields and establish controlled approximation limits for their sewing amplitudes.

  • Presentation-dependent approximation and computational resources. We compare direct Wakimoto and coset constructions of the same limiting current algebra, finding different finite-width errors, regulator dependence and computational costs. An explicit calculation of the coset stress-tensor correlator identifies the effects of regulator corrections in the parent theory. We also examine how parameter sharing and amplitude calibration affect correlation functions, and how sampling methods and computational workloads influence the cost of evaluating them.

  • Finite-mode compression of fermionic state spaces. We study finite-dimensional approximations of fermionic state spaces through polarized mode selection and the resulting sewn amplitudes. Optimized subspaces improve on conventional mode truncation in two of the five conditions studied. Direct and neural optimization give comparable results, with approximation accuracy depending on the retained subspace and observable.

  • Learning from level–rank duality. Modular and fusion data determine correspondences between simple-current orbits in paired WZW theories. We study their use in fusion prediction, finding that the map computed from representation data gives the same predictions as a supplied exact correspondence. We then construct finite-neural charged observables for unknown preparations and use source-sector measurements to predict their paired-sector responses. The transfer is verified in both directions against finite-neural observables and independent KZ transport, without measurements of the target preparations.

For physics readers. WZW models provide an exact algebraic setting in which to study neural realizations of conformal field theories. We construct positive-level affine currents using bosonic Wakimoto and fermionic Fourier–Berezin fields. In the bosonic construction, a direct SU(2)3SU(2)_3 presentation and the SU(6)1/SU(3)2SU(6)_1/SU(3)_2 coset recover the same continuum current sector, while displaying different finite-width corrections and regulator dependence. The fermionic construction realizes paired current algebras within a common free-fermion theory. Its charged sectors admit a CAR/Fock description, with descendant expansions that agree with independent WZW transport calculations. We extend this construction to charged angular observables of the finite neural fields, obtaining controlled approximations to the corresponding sewing amplitudes. Level–rank duality then relates preparations inferred from measurements in one sector to observables in the other. We also examine the approximation of sewn amplitudes using selected fermionic modes and the transfer of fusion data between integrable sectors. Together, these calculations connect the algebraic structure of WZW models with the finite-dimensional and statistical properties of their neural realizations.

For machine learning readers. Our results show how mathematical relations between field theories can inform the design and comparison of neural architectures. Networks with the same limiting current algebra can have substantially different approximation errors at finite width. We find that changing the frequency distribution can improve accuracy without increasing network width, with the preferred distribution depending on the observable and regulator. Different architectures also have different computational costs, and averaging over selected neural parameters can reduce sampling uncertainty. We examine learned compression of fermionic state spaces, finding improvements from the choice of retained modes and comparable performance from direct and neural optimization. Finally, we use level–rank duality in two learning problems. Fusion-label matching can be determined from public representation data, while charged preparations contain unknown information that must be learned from observations. Using explicit finite-neural charged observables, source-trained predictors transfer this information between paired WZW sectors without target-preparation measurements. The experiments also compare these predictions with exact source estimators and direct target training, providing a basis for assessing the benefits and costs of incorporating mathematical structure into neural learning.

The remainder of the paper is organized as follows. § 2 establishes the bosonic and fermionic neural current constructions; § 3 develops charged-state geometry and four-point transport; § 4 analyzes the direct/coset finite-width and resource comparisons; § 5 studies mode compression and transfer learning; and § 6 discusses the outstanding mathematical and computational questions.

Neural architectures and affine current algebras

In this section, we introduce the ingredients for neural-network (NN) realizations of the current algebras appearing in Wess–Zumino–Witten (WZW) models. Our construction uses the neural-network field-theory (NNFT) correspondence, which associates field-theoretic correlation functions with expectation values over ensembles of network parameters [3, 4]. By choosing architectures and priors whose kernels reproduce the required free-field propagators in a certain limit, we are able to use standard free-field representations to construct WZW currents as composite observables of the neural fields and their derivatives.

We consider two complementary constructions. First, we introduce a bosonic substrate consisting of neural realizations of free scalar fields and commuting first-order βγ\beta\gamma ghost fields. Combined with the appropriate nonlinear readouts, derivative corrections, and normal-ordering prescriptions, these implement the Wakimoto representation [29, 30]. Second, we introduce a fermionic substrate consisting of Grassmann-valued neural fields equipped with a Gaussian Berezin functional [33]. In the corresponding operator construction, signed Wick contractions of the elementary fields allow normally ordered fermion bilinears to generate the desired affine current sectors. The two constructions differ both in their elementary statistics and in the composite readouts required to obtain positive level.

Throughout, we distinguish the particular neural substrate specified by the parameterized random fields from the readouts, vacuum, and normal ordering that define the operator construction. This distinction is crucial because, beyond covariance kernels, the exchange statistics and the operator prescription are necessary to specify the algebra of composite operators.

Our target is the positive-level affine current algebra su^(N)K\widehat{\mathfrak{su}}(N)_K, with N≥2N \ge2 and K∈Z>0K \in\mathbb{Z}_{>0}. For convenience, we will fix a set of Hermitian generators tat^a satisfying

tr⁡N(tatb)=δab2,[ta,tb]=ifabctc,a,b,c=1,…,N2−1.(2)\operatorname{tr}_N(t^a t^b) = \frac{\delta^{ab}}{2}, \qquad[t^a,t^b] = i f^{ab}{}_c t^c, \qquad a,b,c=1,\ldots,N^2-1. \tag*{(2)}

This infinite-dimensional algebra can be described by an algebra of holomorphic currents Ja(z)\mathcal{J}^a(z),

Ja(z)Jb(w)∼Kδab2(z−w)2+ifabcJc(w)z−w.(3)\mathcal{J}^a(z)\mathcal{J}^b(w) \sim\frac{K\delta^{ab}}{2(z-w)^2} + \frac{i f^{ab}{}_c \mathcal{J}^c(w)}{z-w}. \tag*{(3)}

The simple pole encodes the underlying su(N)\mathfrak{su}(N) Lie algebra, while the double pole determines its central extension. The coefficient KK is the affine level; the factor of 1/21/2 follows from the normalization of the generators. The Laurent modes of these currents generate the corresponding centrally extended loop algebra.

As in the usual OPE notation, ∼\sim denotes equality up to terms regular as z→wz \to w. In the neural realization, this relation is understood through expectation values over the network parameters in the infinite-width limit: first taken at separated points, after which z→wz \to w while the other insertion points remain separated. Thus (3) is a statement about ensemble correlation functions, and provides our local criterion for realizing the target current algebra.

Bosonic substrate and the Wakimoto construction

The Wakimoto construction uses N−1N-1 Cartan scalars and a commuting βγ\beta\gamma pair for each positive root of su(N)\mathfrak{su}(N) [29, 30],

ϕA,A=1,…,N−1,(βa,γa),a=1,…,N(N−1)2.(4)\phi^A,\qquad A=1,\ldots,N-1,\qquad(\beta^a,\gamma^a),\qquad a=1,\ldots,\frac{N(N-1)}{2}. \tag*{(4)}

The first-order fields have conformal weights (1,0)(1,0) with respect to the Wakimoto stress tensor, and are defined through their OPE,

∂ϕA(z)∂ϕB(w)∼−δAB(z−w)2,βa(z)γb(w)∼−δabz−w,(5)\partial\phi^A(z)\partial\phi^B(w) \sim-\frac{\delta^{AB}}{(z-w)^2},\qquad\beta^a(z)\gamma^b(w) \sim-\frac{\delta^{ab}}{z-w}, \tag*{(5)}

with the reverse-ordered singular product γa(z)βb(w)∼+δab/(z−w)\gamma^a(z)\beta^b(w) \sim+\delta^{ab}/(z-w); all remaining elementary products are regular. The affine currents are then “normal-ordered” polynomials in βa\beta^a, γa\gamma^a, and ∂ϕA\partial\phi^A, together with terms proportional to ∂γa\partial\gamma^a. Their coefficients depend on the Lie algebra and the level. We will come back to their exact definitions at the end of this subsection.

We first define neural architectures with the required elementary correlation functions. We denote the number of independently sampled frequency features by LL.

Both the scalar and βγ\beta\gamma networks use complex frequencies drawn from the same distribution. At width LL, we independently sample complex frequencies Wj=pjeiφjW_j = p_j e^{i\varphi_j}, j=1,…,Lj = 1,\ldots,L, from the rotationally invariant law on the annulus A={W=peiφ:p−<p<p+}A = \{W = p e^{i\varphi}: p_- < p < p_+\},

dνα(ΛB)(W)=1Zα(ΛB)RϵB(p)p1−2α dp dφ2π,Zα(ΛB)=∫p−p+RϵB(p)p1−2α dp,(6)d\nu_{\alpha}^{(\Lambda_B)}(W) = \frac{1}{Z_{\alpha}^{(\Lambda_B)}}\frac{R_{\epsilon_B}(p)}{p^{1-2\alpha}}\,dp\,\frac{d\varphi}{2\pi}, \qquad Z_{\alpha}^{(\Lambda_B)} = \int_{p_-}^{p_+}\frac{R_{\epsilon_B}(p)}{p^{1-2\alpha}}\,dp, \tag*{(6)}

The parameter α∈R\alpha\in\mathbb{R} controls the spectral tilt of the distribution with every real value admissible on a finite annulus. We denote the bosonic regulator data collectively by ΛB=(p−,p+,ϵB)\Lambda_B = (p_-,p_+,\epsilon_B), with momenta expressed in fixed reference units. The regulator RϵB(p)R_{\epsilon_B}(p) suppresses the IR and UV portions of the spectrum, allowing us to take a controlled limit as the annulus fills out the complex plane.

The order of limits is important: we first take the infinite-width limit L→∞L \to\infty at fixed regulator parameters, then remove the annular cutoffs p−→0p_- \to0 and p+→∞p_+ \to\infty at fixed ϵB>0\epsilon_B > 0, and finally consider ϵB→0\epsilon_B \to0 for observables with well-defined continuum limits. A convenient choice for the bosonic construction is the symmetric regulator1

RϵB(p)=e−ϵB(p+1/p).(7)R_{\epsilon_B}(p) = e^{-\epsilon_B(p+1/p)}. \tag*{(7)}

At fixed ϵB\epsilon_B, this suppresses both small and large Fourier features as desired, so the annular cutoffs can be removed while retaining finite correlation functions. The subsequent ϵB→0\epsilon_B \to0 limit is an ordered limit of regulated correlators. In particular, the undifferentiated scalar covariance retains an additive IR divergence, while the IR regulated scheme has well-behaved finite limits. On the full annulus, the normalization is exactly

Zα(0,∞,ϵB)=∫0∞p2α−1e−ϵB(p+p−1) dp=2K2α(2ϵB),(8)Z_{\alpha}^{(0,\infty,\epsilon_B)} = \int_0^\infty p^{2\alpha-1}e^{-\epsilon_B(p+p^{-1})}\,dp = 2K_{2\alpha}(2\epsilon_B), \tag*{(8)}

where KνK_\nu denotes the modified Bessel function of the second kind. The leading small-ϵB\epsilon_B behavior is

References

  1. [1]N. Seiberg and E. Witten, Electric - magnetic duality, monopole condensation, and confinement in N=2 supersymmetric Yang-Mills theory, Nucl. Phys. B 426 (1994) 19–52, [hep-th/9407087].
  2. [2]A. Giveon, M. Porrati and E. Rabinovici, Target space duality in string theory, Phys. Rept. 244 (1994) 77–202, [hep-th/9401139].
  3. [3]J. Halverson, A. Maiti and K. Stoner, Neural Networks and Quantum Field Theory, Mach. Learn. Sci. Tech. 2 (2021) 035002, [2008.08601].DOI
  4. [4]J. Halverson, Building Quantum Field Theories Out of Neurons, 2112.04527.arxiv.org/abs/2112.04527
  5. [5]J. Halverson, J. Naskar and J. Tian, Conformal Fields from Neural Networks, JHEP 10 (2025) 039, [2409.12222].DOI
  6. [6]B. Robinson, Virasoro Symmetry in Neural Network Field Theories, 2512.24420.
  7. [7]S. Yaida, Non-Gaussian processes and neural networks at finite widths, in Proceedings of the First Mathematical and Scientific Machine Learning Conference, pp. 165–192, 2020, 1910.00019.arxiv.org/abs/1910.00019
  8. [8]D. A. Roberts, S. Yaida and B. Hanin, The Principles of Deep Learning Theory. Cambridge University Press, 2022, [2106.10165].
  9. [9]M. Demirtas, J. Halverson, A. Maiti, M. D. Schwartz and K. Stoner, Neural network field theories: non-Gaussianity, actions, and locality, Mach. Learn. Sci. Tech. 5 (2024) 015002, [2307.03223].arxiv.org/abs/2307.03223
  10. [10]C. Ferko and A. Mutchler, Neural Network Field Theory at Finite Width, 2608.21588.
  11. [11]T. R. Harvey, What Neural Network Field Theory Can and Cannot Realise on a Computer, 2608.21523.
  12. [12]T. Cohen and M. Welling, Group equivariant convolutional networks, in International conference on machine learning, vol. 48 of Proceedings of Machine Learning Research, pp. 2990–2999, PMLR, 2016, https://proceedings.mlr.press/v48/cohenc16.html.arxiv.org/abs/1602.07576
  13. [13]R. Kondor and S. Trivedi, On the generalization of equivariance and convolution in neural networks to the action of compact groups, in International conference on machine learning, vol. 80 of Proceedings of Machine Learning Research, pp. 2747–2755, PMLR, 2018, https://proceedings.mlr.press/v80/kondor18a.html.arxiv.org/abs/1802.03690
  14. [14]M. Finzi, S. Stanton, P. Izmailov and A. G. Wilson, Generalizing convolutional neural networks for equivariance to Lie groups on arbitrary continuous data, in International conference on machine learning, vol. 119 of Proceedings of Machine Learning Research, pp. 3165–3176, PMLR, 2020, https://proceedings.mlr.press/v119/finzi20a.html.
  15. [15]A. Bogatskiy, B. Anderson, J. Offermann, M. Roussi, D. Miller and R. Kondor, Lorentz Group Equivariant Neural Network for Particle Physics, in Proceedings of the 37th International Conference on Machine Learning, vol. 119 of Proceedings of Machine Learning Research, pp. 992–1002, PMLR, 2020, https://proceedings.mlr.press/v119/bogatskiy20a.html.arxiv.org/abs/2006.04780
  16. [16]N. Dehmamy, R. Walters, Y. Liu, D. Wang and R. Yu, Automatic symmetry discovery with Lie algebra convolutional network, in Advances in Neural Information Processing Systems, vol. 34, pp. 2503–2515, 2021, https://proceedings.neurips.cc/paper_files/paper/2021/hash/148148d62be67e0916a833931bd32b26-Abstract.html.arxiv.org/abs/2109.07103
  17. [17]T.-Y. Lin, M. Zhu and M. Gharari, Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras, 2024. [2310.04521].arxiv.org/abs/2310.04521
  18. [18]J. Wess and B. Zumino, Consequences of anomalous Ward identities, Physics Letters B 37 (1971) 95–97.DOI
  19. [19]E. Witten, Global Aspects of Current Algebra, Nucl. Phys. B 223 (1983) 422–432.
  20. [20]G. W. Moore and N. Seiberg, Classical and Quantum Conformal Field Theory, Commun. Math. Phys. 123 (1989) 177–254.DOI
  21. [21]D. Gepner and E. Witten, String Theory on Group Manifolds, Nucl. Phys. B 278 (1986) 493–549.DOI
  22. [22]H. Sugawara, A field theory of currents, Phys. Rev. 170 (1968) 1659–1662.DOI
  23. [23]V. G. Kac, Infinite Dimensional Lie Algebras. Cambridge University Press, Cambridge, 3rd ed., 1990, 10.1017/CBO9780511626234.
  24. [24]V. G. Knizhnik and A. B. Zamolodchikov, Current Algebra and Wess-Zumino Model in Two-Dimensions, Nucl. Phys. B 247 (1984) 83–103.
  25. [25]S. G. Naculich, H. A. Riggs and H. J. Schnitzer, Group Level Duality in WZW Models and Chern-Simons Theory, Phys. Lett. B 246 (1990) 417–422.DOI
  26. [26]S. G. Naculich and H. J. Schnitzer, Duality Between SU(N)-k and SU(k)-N WZW Models, Nucl. Phys. B 347 (1990) 687–742.DOI
  27. [27]T. Nakanishi and A. Tsuchiya, Level rank duality of WZW models in conformal field theory, Commun. Math. Phys. 144 (1992) 351–372.DOI
  28. [28]V. Ostrik and M. Sun, Level-Rank Duality via Tensor Categories, Communications in Mathematical Physics 326 (2014) 49–61, [1208.5131].DOI
  29. [29]M. Wakimoto, Fock representations of the affine Lie algebra A₁⁽¹⁾, Commun. Math. Phys. 104 (1986) 605–609.
  30. [30]J. de Boer and L. Feher, Wakimoto realizations of current algebras: An Explicit construction, Commun. Math. Phys. 189 (1997) 759–793, [hep-th/9611083].
  31. [31]V. G. Kač and D. H. Peterson, Infinite-dimensional Lie algebras, theta functions and modular forms, Advances in Mathematics 53 (1984) 125–264.DOI
  32. [32]E. Verlinde, Fusion rules and modular transformations in 2D conformal field theory, Nucl. Phys. B 300 (1988) 360–376.DOI
  33. [33]S. Frank, J. Halverson, A. Maiti and F. Ruehle, Fermions and supersymmetry in neural network field theories, Mach. Learn. Sci. Tech. 7 (2026) 045070, [2511.16741].arxiv.org/abs/2511.16741
  34. [34]Z. Zhang, Optimal architecture and fundamental bounds in neural network field theory, Phys. Rev. D 114 (2026) L061704, [2604.27050].arxiv.org/abs/2604.27050
  35. [35]S. Frank and J. Halverson, String Theory from Infinite Width Neural Networks, 2601.06249.arxiv.org/abs/2601.06249
  36. [36]A. Tsuchiya and Y. Kanie, Vertex Operators in the Conformal Field Theory on P¹ and Monodromy Representations of the Braid Group, Lett. Math. Phys. 13 (1987) 303–312.
  37. [37]A. Tsuchiya, K. Ueno and Y. Yamada, Conformal Field Theory on Universal Family of Stable Curves with Gauge Symmetries, in Integrable Systems in Quantum Field Theory and Statistical Mechanics (M. Jimbo, T. Miwa and A. Tsuchiya, eds.), pp. 459–566. Academic Press, San Diego, 1989. DOI.DOI

Paper details

vlnc:W_fjep9e2p
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Physics and Astronomy

Not recorded for this paper

View statement
Looking for related papers…
Contents