arXiv Machine Learning June 30, 2026 By HakGeun Lee, Hyonho Chun

Identifiability and Stability of Generative Drifting with Companion-Elliptic Kernel Families

Read the original on arXiv Machine Learning →

arXiv:2604. 24196v3 Announce Type: replace-cross Abstract: This paper studies the identifiability and stability of drifting fields in the framework of Generative Modeling via Drifting.

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 Machine Learning

Aug 14

Identifiability and Stability of Generative Drifting in the Companion-Elliptic Kernel Family

arXiv:2604. 24196v4 Announce Type: replace-cross Abstract: A drifting model is a one-step generator trained by moving each sample along a field of kernel-weighted attraction toward data samples and repulsion between model samples; training halts once this field vanishes.

By HakGeun Lee, Hyonho Chun

arXiv Machine Learning

Aug 4

Finite-Probe Total-Variation Certificates for Finite-Basis Drifting Models

arXiv:2608. 01547v1 Announce Type: cross Abstract: Drifting objectives compare a target and model distribution through a vector field observed noisily at finitely many locations.

By Sam Andersson, Ricky Mol\'en

arXiv Machine Learning

Sep 22

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

arXiv:2605.22795v3 Announce Type: replace-cross Abstract: We analyze finite-particle drifting models for one-step generative modeling. For a conservative velocity given by the difference of the kerne...

By Krishnakumar Balasubramanian

safety

arXiv Machine Learning

Aug 4

How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule

arXiv:2608. 01268v1 Announce Type: cross Abstract: Detecting that a stream of high-dimensional embeddings has changed is usually framed as a choice of statistic.

By Adel Kaleche

rag

arXiv Machine Learning

Jul 30

Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport

arXiv:2603. 15384v2 Announce Type: replace-cross Abstract: We improve and extend persistence spheres, introduced in~\cite{pegoraro2025persistence}.

By Matteo Pegoraro

rag

arXiv Machine Learning

Jul 28

When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction

arXiv:2607. 24662v1 Announce Type: new Abstract: Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap.

By Tianpeng Li, Xuan Guo, Wenjun Wang, Wang Zhang, Pengfei Jiao

One email a morning, machine-written

Related stories

Identifiability and Stability of Generative Drifting in the Companion-Elliptic Kernel Family

Finite-Probe Total-Variation Certificates for Finite-Basis Drifting Models

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule

Persistence Spheres: a Bi-continuous Linear Representation of Measures for Partial Optimal Transport

When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction