Spherical mean-field Langevin dynamics concentrate near hidden indices in Gaussian multi-index models with a sharp temperature transition at λ ≃ 1 and achieve d/N and Md/N rates in single-index models via Lévy-Milman concentration.
[Kol06] Vladimir Koltchinskii
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Geometry of Statistical Feature Learning in Mean-Field Langevin Dynamics
Spherical mean-field Langevin dynamics concentrate near hidden indices in Gaussian multi-index models with a sharp temperature transition at λ ≃ 1 and achieve d/N and Md/N rates in single-index models via Lévy-Milman concentration.