# Landau theory of quenched criticality in linear in-context learning

arXiv: https://arxiv.org/abs/2608.28059 · HTML: https://mlsanity.com/paper/2608.28059/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 7 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 2 of 2)

- [Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time](https://mlsanity.com/paper/2510.01098/) (2025)
- [Pretrain-Test Task Alignment Governs Generalization in In-Context Learning](https://mlsanity.com/paper/2509.26551/) (2025)

## Abstract (arXiv)

In-context learning (ICL) allows a pretrained model to infer a new task from examples supplied in its prompt without updating its parameters. In linear models of ICL, the prediction error develops a double-descent singularity when the number of pretraining samples becomes comparable to the number of learnable parameters. We formulate this interpolation singularity as a critical phenomenon of a quenched disordered system. By comparing annealed and quenched descriptions of the same linear ICL model, we identify the connected sample-to-sample fluctuations of the learned parameters as the microscopic origin of the singular error. A Landau potential is constructed by integrating the cavity self-consistency equation for the renormalized ridge parameter xi. The role of (magnetization) order parameter is played by xi, while the bare ridge parameter λ becomes its conjugate magnetic field. The normalized sample complexity τ acts as a temperature and the double-descent singularity occurs at the critical temperature τc =1. The Landau susceptibility is precisely the quantity that diverges in the fluctuation contribution to the prediction error. The order parameter is closely related to the fraction of zero eigenvalues of the empirical relaxation matrix in the ridgeless limit, which define flat directions in the learning dynamics. The Landau theory is generically cubic in the order parameter with critical exponents (βrm cr,δrm cr,γrm cr)=(1,2,1). In the large-context regime, there appears a pseudogap-like regime characterized by suppressed order parameter. Predictions of the Landau theory are independently confirmed from numerical solutions of the original learning problem with good quantitative agreement. Our results pave the way for solid statistical-physics understanding of the interpolation criticality in linear in-context learning.