arXiv Machine Learning September 4, 2026 By Zachary P Bradshaw

What is Smoothness?

Read the original on arXiv Machine Learning →

arXiv:2609. 03246v1 Announce Type: cross Abstract: Smoothness of a function on the real line is reflected in the decay of its Fourier transform, which suggests that smoothness of a function in $L^2(G)$ for a group $G$ should mean concentration of the Fourier coefficients at low frequency.

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 AI

Jul 29

Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientist

arXiv:2607. 24847v1 Announce Type: cross Abstract: We introduce an extremal invariant associated with Chowla-type order conditions in finite groups.

By Mohsen Aliabadi, Keith Driscoll, Elliot Krop, Petar Sirkovic, Everett Sullivan, Elahe Vedadi

arXiv Machine Learning

Jul 13

Group Invariant Spectral Embedding

arXiv:2607. 08987v1 Announce Type: new Abstract: Spectral embedding methods are widely used for dimensionality reduction and clustering of high-dimensional datasets with intrinsic low-dimensional structures.

By Yeari Vigder, Paulina Hoyos, David Thong, Joakim and\'en, Joe Kileel, Amit Moscovich

rag

arXiv Machine Learning

Jul 16

What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry

arXiv:2607. 13046v1 Announce Type: new Abstract: We develop a framework for the information discarded by machine learning models whose inputs carry a Lie group action.

By Zachary P. Bradshaw

computer-vision safety

arXiv Machine Learning

Aug 4

Polyatomic Complexes: A topologically-informed learning representation for atomistic systems

arXiv:2409. 15600v3 Announce Type: replace Abstract: A representation of a molecule or material should be invariant to the symmetries of physics, unique, continuous, efficient and general.

By Rahul Khorana, Marcus Noack, Jin Qian

llms

arXiv AI

Jul 7

An AI-Assisted Solution to the Signed BAR Conjecture: Uniqueness in the Harrison--Reiman Class and a Completely-$\mathcal{S}$ Class Obstruction

arXiv:2607. 03639v1 Announce Type: cross Abstract: For a multidimensional reflected diffusion, determining whether the associated basic adjoint relationship (BAR) uniquely characterizes the stationary distribution is a basic uniqueness problem in the BAR approach.

By Yiping Lu, Youheng Zhu

llms diffusion

arXiv AI

Sep 16

On the Expressive Power of Implicit Line-Graph Higher-Order Weisfeiler--Leman

arXiv:2609.16412v1 Announce Type: cross Abstract: Whitney's theorem allows isomorphism testing for connected simple graphs, apart from $K_3$ and $K_{1,3}$, to be formulated as distinguishing their li...

By Fan Yang

One email a morning, machine-written

Related stories

Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientist

Group Invariant Spectral Embedding

What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry

Polyatomic Complexes: A topologically-informed learning representation for atomistic systems

An AI-Assisted Solution to the Signed BAR Conjecture: Uniqueness in the Harrison--Reiman Class and a Completely-$\mathcal{S}$ Class Obstruction

On the Expressive Power of Implicit Line-Graph Higher-Order Weisfeiler--Leman