arXiv Machine Learning June 15, 2026 By Siddharth Pal, Viktoria Rojkova

A Stationarity-and-Coupling Criterion for Training-Free Time-Lagged Spectral Embeddings of Multivariate Time Series

Read the original on arXiv Machine Learning →

arXiv:2606. 13823v1 Announce Type: new Abstract: We study training-free fixed-length descriptors for multivariate time series and ask not merely whether such a descriptor performs well, but when it can be expected to work at all.

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

arXiv AI

Jul 15

Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG

arXiv:2607. 11950v1 Announce Type: cross Abstract: Brain field potentials are scale-free: their power spectra follow a $1/f^{\beta}$ law whose aperiodic exponent $\beta$ tracks cortical state, and sleep depth in particular is a shift in $\beta$.

By Dibakar Sigdel

llms benchmarks safety

arXiv AI

Jun 3

Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group

arXiv:2606. 03003v1 Announce Type: cross Abstract: A latent world model built from an equivariant encoder $E$ and an equivariant predictor $f$ inherits a provable symmetry of its training loss: when the world's dynamics genuinely carries a group $G$ acting on latents by an orthogonal representation $\rho(g)$, the one-step prediction relMSE is exactly invariant across the whole group, so fitting the dynamics on a restricted slice of orientations mathematically determines it on the entire orbit (j\v{u} y\=i f\v{a}n s\=an).

By Hongbo Wang (Stony Brook University)

arXiv Machine Learning

Jul 15

The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting

arXiv:2607. 13006v1 Announce Type: new Abstract: A growing family of indices scores how predictable a series is from its spectrum.

By Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban

benchmarks

arXiv Machine Learning

Jul 15

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

arXiv:2607. 12735v1 Announce Type: new Abstract: Companion work showed the grokking delay is causally the time to form task-structured representations, injectable via a contrastive prior.

By Gunner Levi Howe

safety

arXiv AI

Jun 3

Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate

arXiv:2606. 02670v1 Announce Type: cross Abstract: Many recent multivariate time series anomaly detection (MT-SAD) models incorporate cross-channel modeling, under the implicit assumption that the structure of anomalies may be spread across multiple channels.

By Marc Pinet (LIG), Julien Cumin (LIG), Samuel Berlemont (LIG), Dominique Vaufreydaz (LIG)

benchmarks

arXiv Machine Learning

Jun 25

A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis

arXiv:2606. 24903v1 Announce Type: new Abstract: Deciding when to stop collecting labeled examples is a fundamental but undertheorized problem in applied machine learning.

By Arnav Gupta

Related stories

Scale-Aware Attention for Scarce Neural Data: An RG-Flow Transformer on Sleep-EDF EEG

Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group

The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate

A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis