arXiv Machine Learning June 30, 2026 By Igor Halperin

Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions

Read the original on arXiv Machine Learning →

arXiv:2606. 29679v1 Announce Type: new Abstract: Observable Matrix Dynamics (OMD) is a diagnostic framework that probes the dynamics of high-dimensional internal representations of inputs by a neural network via a fixed-size $N \times N$ distance matrix $M(t)$ on a held set of $N$ inputs.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 30

I-BBS: Coordinate-Free Inference of Latent Sub-Manifolds Using Random Distance Matrix Theory

arXiv:2606. 29675v1 Announce Type: new Abstract: Bogomolny, Bohigas and Schmit (BBS) found that the spectrum of the pairwise distance matrix on N points sampled from a smooth d-dimensional manifold encodes a signature of the underlying geometry.

By Igor Halperin

rag

arXiv Machine Learning

Jun 30

Spectral phase transitions and trainability in neural network learning dynamics

arXiv:2606. 28486v1 Announce Type: cross Abstract: The emergence of low-dimensional structures in the spectra of neural network weight matrices is a common empirical feature of trained models, but the dynamical origin of this phenomenon during learning remains an open problem.

By Chanju Park, Dario Bocchi, Francesco D'Amico, Biagio Lucini, Gert Aarts

safety

arXiv AI

Jul 7

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

arXiv:2602. 02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed.

By Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan

diffusion

arXiv Machine Learning

Jul 7

In-span learning: adapting reduced-order models using their own predictions

arXiv:2607. 02937v1 Announce Type: new Abstract: Reduced-order models compress high-dimensional dynamics into low-dimensional representations that can be evaluated rapidly, but they lose accuracy when online dynamics drift beyond the training data.

By Amirpasha Hedayat, Laura Balzano, Karthik Duraisamy

llms

Hugging Face Trending Papers

Jun 29

Scalar Representations of Neural Network Training Dynamics

Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of trainable parameters makes the direct analysis of these dynamics challenging.

rag

arXiv AI

Jul 2

Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning

arXiv:2607. 00063v1 Announce Type: cross Abstract: This paper studies how spectral geometry emerges in quantum learning models and how it can be diagnosed with physically grounded probes.

By Santanu Ganguly, Xing Liang, Dimitrios Makris

Related stories

I-BBS: Coordinate-Free Inference of Latent Sub-Manifolds Using Random Distance Matrix Theory

Spectral phase transitions and trainability in neural network learning dynamics

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

In-span learning: adapting reduced-order models using their own predictions

Scalar Representations of Neural Network Training Dynamics

Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning