arXiv Machine Learning August 17, 2026 By Taegyun Kim

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

Read the original on arXiv Machine Learning →

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 $q$.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Statistics ML

Sep 24

Optimal State-Space Order for Spectral Gaps of Sliding-Window Occupation Counts

arXiv:2609.27836v1 Announce Type: cross Abstract: Let $P$ be an irreducible reversible Markov kernel on a $m$-state space $\Omega$, and denote its right spectral gap $\gamma=1-\lambda_2(P)$. From a s...

By Yanjin Xiang, Zhihua Zhang

arXiv Machine Learning

Sep 18

TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models

arXiv:2609. 20577v1 Announce Type: cross Abstract: We study the Bayes-optimal spherical linear model as the ambient dimension and sample size grow proportionally, under a quantitative Marchenko--Pastur spectral-regularity condition on the design.

By Jingbo Liu, Zhiyuan Yu

arXiv AI

Sep 15

Edge-addition monotonicity of positive p-energy fails for every p >= 1

arXiv:2609.13476v1 Announce Type: cross Abstract: At a 2021 AIM workshop, Guo conjectured that the positive square energy s+ = E+_2 should inherit the familiar edge-addition monotonicity of the spect...

By Koyar Afrasyab

arXiv Machine Learning

Sep 17

Symmetry without a manifold: intrinsic dimension on orbits

arXiv:2609. 17926v1 Announce Type: new Abstract: The standard geometric derivation of neural scaling exponents takes the intrinsic dimension of a data manifold as its input.

By Chon-Fai Kam, Miloud Bessafi, Fr\'ed\'eric Cadet

arXiv Machine Learning

Aug 19

Fourth-Moment Geometry of Rademacher Sums

arXiv:2608. 17802v1 Announce Type: new Abstract: Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher signs and let $a=(a_1,\ldots,a_n)\in\R^n$ satisfy the normalization below.

By Peigan Gao, Jian Qian

llms efficiency

arXiv Machine Learning

Jul 14

Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress

arXiv:2607. 09906v1 Announce Type: cross Abstract: We present, to our knowledge, the first adaptation of Pauli Correlation Encoding (PCE) to quantum topological data analysis, reformulating Betti number estimation as a depth-efficient variational optimization over a compressed qubit register.

By Arul Rhik Mazumder, Shreyan Ronit Mazumder

rag

One email a morning, machine-written

Related stories

Optimal State-Space Order for Spectral Gaps of Sliding-Window Occupation Counts

TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models

Edge-addition monotonicity of positive p-energy fails for every p >= 1

Symmetry without a manifold: intrinsic dimension on orbits

Fourth-Moment Geometry of Rademacher Sums

Depth-Efficient Quantum Topological Data Analysis for Regime-Specific Detection of Financial Stress