arXiv Machine Learning

Non-Shattering at and Above the Dynamical Temperature in the Spherical Pure p-Spin Model

arXiv:2608. 14369v1 Announce Type: cross Abstract: We consider the notion of shattering introduced by Ben Arous and Jagannath for spherical pure $p$-spin glasses with overlap $q$.

arXiv Machine Learning
Sep 4

Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails

The paper investigates restricted eigenvalue (RE) bounds for norm‑regularized estimators under heavy‑tailed designs. It shows that the previously conjectured sample‑size law based on Gaussian width fails for heavy‑tailed measurements, due to a phenomenon called simultaneous threshold occupancy. The authors provide explicit counterexamples, derive worst‑case sample‑complexity bounds, and compare the behavior of heavy‑tailed versus Gaussian designs on constant‑width polyhedral descent cones.

By Shi Fu, Huibo Xu, Qixin Zhang, Dacheng Tao
arXiv Machine Learning
Aug 18

Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run

arXiv:2608. 16878v1 Announce Type: cross Abstract: For any convex body $\mathcal{K}\subset\mathbb{R}^{n}$ containing a unit ball, the spectral gap of Hit-and-Run is $\Omega(1/(n^2 C_{\mathsf{PI}}))$, where $C_{\mathsf{PI}}$ is the Poincar\'e constant of the uniform distribution $\pi$ over $\mathcal{K}$.

By Yunbum Kook, Santosh S. Vempala