arXiv Machine Learning August 10, 2026 By Albert Saiapin, Kim Batselier

Tensor Network Kernel Machines: A JAX Framework for Machine Learning and Nonlinear System Identification

Read the original on arXiv Machine Learning →

arXiv:2608. 07043v1 Announce Type: cross Abstract: Developing nonlinear models that are both expressive and computationally efficient remains a challenge in machine learning and nonlinear system identification.

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

benchmarks

arXiv Machine Learning

Jun 10

Hyperparameter Learning for Latent Factorization of Tensors for Representation Learning to Large-scale Dynamic Weighted Directed Network

arXiv:2606. 09880v1 Announce Type: new Abstract: Large-scale dynamic weighted directed networks (DWDNs) are widely used to model time-varying interactions among nodes.

By Yaqian Zhan, Jialan He, Tianzhu Chen

rag

arXiv AI

Jul 2

K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks

arXiv:2607. 00329v1 Announce Type: cross Abstract: Recursive Feature Machines (RFMs) are a class of kernel machines that utilize the Average Gradient Outer Product (AGOP) as a mechanism for feature learning.

By Gil Pasternak

arXiv AI

Jul 7

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks

arXiv:2606. 00130v2 Announce Type: replace-cross Abstract: Large deep neural networks are costly to store and deploy because inference must move and evaluate many parameters.

By Andrzej Cichocki, Michal Wietczak

efficiency

arXiv Machine Learning

Jul 20

(MPO)$^2$: Multivariate Polynomial Optimization based on Matrix Product Operators

arXiv:2607. 15916v1 Announce Type: new Abstract: Central to machine learning and signal processing is the ability to perform universal function approximation and learn complex input-output relationships from limited numbers of observations.

By Niccol\`o Ciolli, Anders Vestergaard N{\o}rskov, Michael Kastoryano, Petr Taborsky, Morten M{\o}rup

rag benchmarks

arXiv Machine Learning

Jun 17

A tensor network approach for chaotic time series prediction

arXiv:2505. 17740v2 Announce Type: replace Abstract: Making accurate predictions of chaotic time series is a complex challenge.

By Rodrigo Mart\'inez-Pe\~na, Rom\'an Or\'us

benchmarks

arXiv Machine Learning

6d ago

Kernel Methods for Learning Operators with Multiple Inputs and Outputs

arXiv:2608. 11831v1 Announce Type: new Abstract: Learning mappings between infinite-dimensional objects is a central challenge in scientific machine learning.

By Adrien Weihs, Chunyang Liao, Jingmin Sun, Hayden Schaeffer

benchmarks

Related stories

Hyperparameter Learning for Latent Factorization of Tensors for Representation Learning to Large-scale Dynamic Weighted Directed Network

K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks

(MPO)$^2$: Multivariate Polynomial Optimization based on Matrix Product Operators

A tensor network approach for chaotic time series prediction

Kernel Methods for Learning Operators with Multiple Inputs and Outputs