arXiv Statistics ML

A Mechanistic Interpretation of Prescribed-Parameter Convolutional Kernels

The paper investigates why prescribed‑parameter convolutional kernels, such as those used in ROCKET and its variants, perform well on time‑series classification. It analyzes the proportion of positive values (PPV) pooling operator, proving exact invariance to circular translations and quantifying deviations under finite boundaries. Experiments on the UCR collection show that increasing kernel count yields diminishing returns, while longer kernels raise effective dimensionality and distance correlation, with optimal test performance at intermediate lengths.

arXiv Machine Learning

Aug 20

Multi-Class Electrical and Mechanical Fault Classification Using Random Convolutional Kernels

The paper evaluates SelF‑Rocket, a random convolutional kernel-based method, for multi‑class diagnosis of mechanical and electrical faults in rotating machinery. It introduces a multivariate extension of SelF‑Rocket and compares it with leading ROCKET‑based methods on two public benchmarks, MaFaulDa and ITSC‑UDG. Results show SelF‑Rocket achieves the best accuracy‑latency trade‑off, excelling on MaFaulDa and remaining competitive on the more challenging ITSC‑UDG dataset.

By Mouhamadou Mansour Lo, Mouad Talbaoui, Gildas Morvan, Mathieu Rossi, Fabrice Morganti, David Mercier

benchmarks

arXiv Machine Learning

Jun 4

Generating Financial Time Series by Matching Random Convolutional Features

arXiv:2606. 05138v1 Announce Type: new Abstract: Generating realistic financial time series is challenging as training data is often limited to a single historical path.

By Konrad J. Mueller, Nikita Zozoulenko, Ben Wood, Thomas Cass, Lukas Gonon

diffusion safety

arXiv AI

Jun 24

Zero-Shot Test-Time Canonicalization using Out-of-Distribution Scoring

arXiv:2606. 24178v1 Announce Type: cross Abstract: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged.

By Dominik Lindner, Johann Schmidt, Tom Siegl, Martin Becker, Sebastian Stober

benchmarks

arXiv Machine Learning

Oct 2

TopTimeNet: Topologically-assisted time-series classification model

arXiv:2609.39792v2 Announce Type: new Abstract: Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned arch...

By Sharareh Sayyad, Sophia Bazzi

llms rag benchmarks

arXiv Machine Learning

Sep 10

Minimum distance classification for nonlinear dynamical systems

The paper introduces Dynafit, a kernel-based method for classifying trajectories produced by distinct nonlinear dynamical systems. It learns a distance metric by approximating the Koopman operator, enabling classification in a feature space without explicit dimensionality. The authors demonstrate Dynafit on logistic map chaos detection, handwritten dynamical pattern recognition, and visual dynamic texture classification.

By Dominique Martinez

arXiv Machine Learning

Jul 22

In-Context Time Series Classification with Random Convolutional Features

arXiv:2607. 19234v1 Announce Type: new Abstract: Time series classification is central to domains like medical signal analysis, industrial monitoring, and sensor-based activity recognition, where class information manifests as localized shapes, specific frequencies, temporal shifts, or complex cross-channel interactions.

By Joscha C\"uppers, Jilles Vreeken

benchmarks

arXiv Machine Learning

Jun 17

Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data

arXiv:2605. 29669v2 Announce Type: replace-cross Abstract: Recent work in random matrix theory (RMT) has developed the notion of deterministic equivalents: typically linear surrogate models that approximate the spectral behavior of large nonlinear random matrices, such as nonlinear feature maps in neural networks (NNs).

By Collin Cranston, Zhichao Wang, Todd Kemp, Michael W. Mahoney

Hugging Face Trending Papers

Sep 30

TopTimeNet: Topologically-assisted time-series classification model

Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned architectures must discover both a representation and...

llms rag benchmarks

arXiv Machine Learning

Jul 3

Transformer Geometry Observatory TGO-II: Representational Similarity Observatory

arXiv:2607. 02386v1 Announce Type: cross Abstract: While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood.

By Kaustubh Kapil, Kishor P. Upla

llms computer-vision safety

arXiv Machine Learning

Oct 19

Is a Linear Probe Evidence of a Linear Representation?

arXiv:2610.22655v1 Announce Type: cross Abstract: The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space,...

By Nadir Kutluozen, Christian Intern\`o, David Klindt

llms benchmarks

arXiv Machine Learning

Aug 7

Time Series Classification through Diffeomorphic Time Warping (DiffTW)

arXiv:2606. 23472v2 Announce Type: replace-cross Abstract: Time series classification involves learning a mapping from a continuous, temporally ordered sequence of real-valued observations to discrete response variables, like class labels.

By Vicky Geneva Haney, Kamel Lahouel, Victor Rielly, Bruno M. Jedynak

safety

arXiv Machine Learning

Jun 2

Revisiting Neural Processes via Fourier Transform and Volterra Series

arXiv:2606. 01172v1 Announce Type: new Abstract: Modeling unknown latent functions from finite, irregularly sampled measurements is a recurring challenge across science and engineering.

By Peiman Mohseni, Nick Duffield, Raymond K. W. Wong

benchmarks safety

Related stories