arXiv Machine Learning June 10, 2026 By Yaqian Zhan, Jialan He, Tianzhu Chen

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

Read the original on arXiv Machine Learning →

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

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 AI

Jun 4

An Ensembled Latent Factor Model via Differential Evolution and Gradient Descent Optimization

arXiv:2606. 04408v1 Announce Type: cross Abstract: High-dimensional and incomplete (HDI) data are prevalent in many real-world big data scenarios.

By Rui Zhang, Jinhang Liu, Wenbo Zhang

arXiv AI

Jul 3

MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning

arXiv:2506. 09105v3 Announce Type: replace-cross Abstract: We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers.

By Javier Lopez-Piqueres, Pranav Deshpande, Archan Ray, Mattia J. Villani, Marco Pistoia, Niraj Kumar

llms fine-tuning benchmarks

arXiv Machine Learning

Aug 10

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

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.

By Albert Saiapin, Kim Batselier

benchmarks

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 AI

Sep 15

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks

The paper discusses tensorizing neural networks by reshaping dense weight matrices into higher-order tensors and approximating them with low-rank tensor network decompositions. This approach offers promising model compression and introduces bond indices that create new latent spaces, potentially enhancing interpretability. Despite encouraging empirical results, tensorized neural networks remain underused, and the authors call for more research to address practical scaling and adoption challenges.

By Safa Hamreras, Sukhbinder Singh, Rom\'an Or\'us

efficiency safety

arXiv Machine Learning

Jun 30

Scalar Representations of Neural Network Training Dynamics

arXiv:2606. 30384v1 Announce Type: new Abstract: Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape.

By Pedro Jim\'enez-Gonz\'alez, Miguel C. Soriano, Lucas Lacasa

rag

One email a morning, machine-written

Related stories

An Ensembled Latent Factor Model via Differential Evolution and Gradient Descent Optimization

MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning

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

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

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks

Scalar Representations of Neural Network Training Dynamics