mlsanityData to 14 Oct 2026

A Sharp Universality Dichotomy for the Free Energy of Spherical Spin Glasses

arXiv 2601.08599 ↗First posted 13 Jan 2026math.PR math-ph math.MPcited by 0

Not on the map. Why?

Abstract (arXiv)

We study the free energy for pure and mixed spherical p-spin models with i.i.d. disorder. In the mixed case, each p-interaction layer is assumed either to have regularly varying tails with exponent αp or to satisfy a finite 2p-th moment condition. For the pure spherical p-spin model with regularly varying disorder of tail index α, we introduce a tail-adapted normalization that interpolates between the classical Gaussian scaling and the extreme-value scale, and we prove a sharp universality dichotomy for the quenched free energy. In the subcritical regime α<2p, the thermodynamics is driven by finitely many extremal couplings and the free energy converges to a non-degenerate random limit described by the NIM (non-intersecting monomial) model, depending only on extreme-order statistics. At the critical exponent α=2p, we obtain a random one-dimensional TAP-type variational formula capturing the coexistence of an extremal spike and a universal Gaussian bulk on spherical slices. In the supercritical regime α>2p (more generally, under a finite 2p-th moment assumption), the free energy is universal and agrees with the deterministic Crisanti--Sommers/Parisi value of the corresponding Gaussian model, as established in [Sawhney-Sellke'24]. We then extend the subcritical and critical results to mixed spherical models in which each p-layer is either heavy-tailed with αp≤ 2p or has finite 2p-th moment. In particular, we derive a TAP-type variational representation for the mixed model, yielding a unified universality classification of the quenched free energy across tail exponents and mixtures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 36 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

5 of 36 references.

References · 5

  1. 2018Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learningcited by 215
  2. 2019A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networkscited by 214
  3. 2014A statistical model for tensor PCAcited by 72
  4. 2024Emergence of heavy tails in homogenized stochastic gradient descentcited by 4
  5. 2025Global law of conjugate kernel random matrices with heavy-tailed weightscited by 3

Built on by

Not cited yet.