HEXAGONbeta

Parisi formula for Ising and Spherical Perceptrons

Primarily AI-generated textHuman understanding: some partsmath.PR — Probabilitymath-ph — Mathematical Physics

Contributed by Daniel Fu ↗, Youngtak Sohn ↗

Version 1 / Oct 08, 2026 / CC BY 4.0

Abstract

We prove a Parisi formula for Ising and spherical perceptrons with Gaussian disorder and i.i.d. random potentials having a common Lipschitz bound and integrable values at zero. We assume M/N→α∈(0,∞)M/N\to\alpha\in(0,\infty), where MM is the number of Gaussian vectors and NN is the number of spins. The proof combines cavity in MM and NN with the Aizenman–Sims–Starr scheme for the lower bound and Guerra’s interpolation for the upper bound. As consequences, we answer several problems posed by Talagrand (2011) and establish a quenched large deviation principle for the empirical distribution of the Gaussian projections, resolving a conjecture of Bolthausen and Kistler (2010). We also resolve the sharp-threshold conjecture of Aubin, Perkins, and Zdeborová (2019) for the uu-function binary perceptron at every positive width, and establish the predicted variational formulas for the entropy and capacity of the negative spherical perceptron. Finally, the zero-temperature limit yields the scalar projection-pursuit formulas conjectured by Montanari and Zhou (2025, 2026), in both the supervised and unlabelled settings.

Provenance statement

This document and its arguments were generated through discussions with ChatGPT 5.6 Pro. An initial draft for the capacity of the negative spherical perceptron was generated on July 15, 2026, and we extended the argument to i.i.d. lipschitz potentials, both Ising and spherical, on September 17, 2026. While distilling the main ideas, carefully checking the proof, and polishing the draft, we learned on October 6, 2026, that OpenAI had released overlapping results across three manuscripts~\cite{OpenAIIsingPerceptron2026,OpenAISphericalPerceptron2026,OpenAIJamming2026}. Given these circumstances, we decided to post this working draft on Hexagon.

Tools used

OpenAI
ChatGPTVersion 5.6Pro
OpenAI
ChatGPTVersion 6

References

  1. A. Adhikari, Spin distributions for generic spherical spin glasses , Electron. J. Probab. 27 (2022); doi:10.1214/22-EJP755; arXiv:1907.03847.arXivDOI
  2. M. Aizenman, R. Sims, and S. L. Starr, Extended variational principle for the Sherrington--Kirkpatrick spin-glass model , Phys. Rev. B 68 (2003), no. 21, 214403; doi:10.1103/PhysRevB.68.214403.DOI
  3. B. Aubin, W. Perkins, and L. Zdeborová, Storage capacity in symmetric binary perceptrons , J. Phys. A: Math. Theor. 52 (2019), no. 29, 294003; doi:10.1088/1751-8121/ab227a; arXiv:1901.00314.arXivDOI
  4. M. Benedetti, A. Bogdanov, E. M. Malatesta, M. Mézard, G. Perrupato, A. Rosen, N. I. Schwartzbach, and R. Zecchina, Overlap gap and computational thresholds in the square wave perceptron , J. Stat. Mech. Theory Exp. (2025), no. 12, 123303; doi:10.1088/1742-5468/ae23be; arXiv:2506.05197.arXivDOI
  5. G. J. Bex, R. Serneels, and C. Van den Broeck, Storage capacity and generalization error for the reversed-wedge Ising perceptron , Phys. Rev. E 51 (1995), no. 6, 6309--6312; doi:10.1103/PhysRevE.51.6309.DOI
  6. E. Bolthausen and N. Kistler, A quenched large deviation principle and a Parisi formula for a perceptron version of the GREM , in Probability in Complex Physical Systems , Springer Proceedings in Mathematics, vol. 11, Springer, Berlin, Heidelberg, 2012, pp. 425--442; doi:10.1007/978-3-642-23811-6_17; arXiv:1011.5686.arXivDOI
  7. E. Bolthausen, S. Nakajima, N. Sun, and C. Xu, Gardner formula for Ising perceptron models at small densities , Proceedings of Machine Learning Research 178 (2022), 1787--1911; arXiv:2111.02855.arXiv
  8. E. Bolthausen and A.-S. Sznitman, On Ruelle's probability cascades and an abstract cavity method , Commun. Math. Phys. 197 (1998), 247--276; doi:10.1007/s002200050450.DOI
  9. H.-B. Chen, V. Issa, and J.-C. Mourrat, Free energy of non-convex multi-species spin glasses with centered Ising spins , arXiv:2606.16636, 2026.arXiv
  10. W.-K. Chen, The Aizenman--Sims--Starr scheme and Parisi formula for mixed pp-spin spherical models , Electron. J. Probab. 18 (2013), article no. 94, 1--14; doi:10.1214/EJP.v18-2580; arXiv:1204.5115.arXivDOI
  11. T. M. Cover, Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition , IEEE Trans. Electron. Comput. EC-14 (1965), no. 3, 326--334; doi:10.1109/PGEC.1965.264137.DOI
  12. A. Dembo and O. Zeitouni, Large Deviations Techniques and Applications , second edition, corrected printing of the 1998 edition, Stochastic Modelling and Applied Probability, vol. 38, Springer, Berlin, Heidelberg, 2010; doi:10.1007/978-3-642-03311-7.DOI
  13. S. Franz and G. Parisi, The simplest model of jamming , J. Phys. A: Math. Theor. 49 (2016), no. 14, 145001; doi:10.1088/1751-8113/49/14/145001; arXiv:1501.03397.arXivDOI
  14. E. Gardner, The space of interactions in neural network models , J. Phys. A: Math. Gen. 21 (1988), no. 1, 257--270; doi:10.1088/0305-4470/21/1/030.DOI
  15. E. Gardner and B. Derrida, Optimal storage properties of neural network models , J. Phys. A: Math. Gen. 21 (1988), no. 1, 271--284; doi:10.1088/0305-4470/21/1/031.DOI
  16. G. Györgyi and P. Reimann, Beyond storage capacity in a single model neuron: continuous replica symmetry breaking , J. Stat. Phys. 101 (2000), nos. 1--2, 679--702; doi:10.1023/A:1026441500710; arXiv:cond-mat/0003360.arXivDOI
  17. A. Jagannath and I. Tobasco, A dynamic programming approach to the Parisi functional , Proc. Amer. Math. Soc. 144 (2016), no. 7, 3135--3150; doi:10.1090/proc/12968; arXiv:1502.04398.arXivDOI
  18. W. Krauth and M. Mézard, Storage capacity of memory networks with binary couplings , J. Phys. (Paris) 50 (1989), no. 20, 3057--3066; doi:10.1051/jphys:0198900500200305700.DOI
  19. A. Montanari and K. Zhou, Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time? , Ann. Probab., to appear; arXiv:2406.02970v3, 2025.arXiv
  20. A. Montanari and K. Zhou, Replica symmetry breaking and algorithmic thresholds in empirical risk minimization under multi-index model , arXiv:2606.28573v1, 2026.arXiv
  21. J.-C. Mourrat and D. Panchenko, Extending the Parisi formula along a Hamilton--Jacobi equation , Electron. J. Probab. 25 (2020), Paper No. 23, 17 pp.; doi:10.1214/20-EJP432; arXiv:1910.14482.arXivDOI
  22. S. Nakajima and N. Sun, Sharp threshold sequence and universality for Ising perceptron models , Proceedings of the 2023 Annual ACM--SIAM Symposium on Discrete Algorithms (SODA), 638--674, SIAM, 2023; doi:10.1137/1.9781611977554.ch28; arXiv:2204.03469.arXivDOI
  23. OpenAI, The free energy of the Ising random perceptron , manuscript, September 24, 2026; https://github.com/openai/math/blob/main/preprints/The-free-energy-of-the-Ising-random-perceptron-September-24-2026/The-free-energy-of-the-Ising-random-perceptron-September-24-2026.pdf OpenAI mathematics repository .link
  24. OpenAI, The free energy of the spherical random perceptron , manuscript, September 24, 2026; https://github.com/openai/math/blob/main/preprints/The-free-energy-of-the-spherical-random-perceptron-September-24-2026/The-free-energy-of-the-spherical-random-perceptron-September-24-2026.pdf OpenAI mathematics repository .link
  25. OpenAI, Microscopic jamming in the negative spherical perceptron , OpenAI Math Release preprint, September 24, 2026; https://github.com/openai/math/blob/main/preprints/Microscopic-jamming-in-the-negative-spherical-perceptron-September-24-2026/Microscopic-jamming-in-the-negative-spherical-perceptron-September-24-2026.pdf OpenAI mathematics repository .link
  26. D. Panchenko, The Sherrington--Kirkpatrick Model , Springer Monographs in Mathematics, Springer, 2013; doi:10.1007/978-1-4614-6289-7.DOI
  27. D. Panchenko, The free energy in a multi-species Sherrington--Kirkpatrick model , Ann. Probab. 43 (2015), no. 6, 3494--3513; doi:10.1214/14-AOP967; arXiv:1310.6679.arXivDOI
  28. D. Panchenko and M. Talagrand, On one property of Derrida--Ruelle cascades , C. R. Math. Acad. Sci. Paris 345 (2007), no. 11, 653--656; doi:10.1016/j.crma.2007.10.035.DOI
  29. D. Panchenko and M. Talagrand, Guerra's interpolation using Derrida--Ruelle cascades , preprint, arXiv:0708.3641 (2007).arXiv
  30. F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain , Psychol. Rev. 65 (1958), no. 6, 386--408; doi:10.1037/h0042519.DOI
  31. D. Ruelle, A mathematical reformulation of Derrida's REM and GREM , Commun. Math. Phys. 108 (1987), no. 2, 225--239; doi:10.1007/BF01210613.DOI
  32. M. Shcherbina and B. Tirozzi, Rigorous solution of the Gardner problem , Commun. Math. Phys. 234 (2003), no. 3, 383--422; doi:10.1007/s00220-002-0783-3; arXiv:math-ph/0112003.arXivDOI
  33. Z. Šidák, Rectangular confidence regions for the means of multivariate normal distributions , J. Amer. Statist. Assoc. 62 (1967), no. 318, 626--633; doi:10.1080/01621459.1967.10482935.DOI
  34. M. Talagrand, Mean Field Models for Spin Glasses, Volume I: Basic Examples , Ergebnisse der Mathematik und ihrer Grenzgebiete, vol. 54, Springer, 2011; doi:10.1007/978-3-642-15202-3.DOI
  35. M. Talagrand, Mean Field Models for Spin Glasses, Volume II: Advanced Replica-Symmetry and Low Temperature , Ergebnisse der Mathematik und ihrer Grenzgebiete, vol. 55, Springer, 2011; doi:10.1007/978-3-642-22253-5.DOI
  36. M. Talagrand, Free energy of the spherical mean field model , Probab. Theory Related Fields 134 (2006), 339--382; doi:10.1007/s00440-005-0433-8.DOI

Version history

  1. v1Submitted by Youngtak SohnInitial depositCurrentOct 07, 2026