arXiv AI
Understanding Deep Learning via Notions of Rank
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 22
Spectral Higher-Order Neural Networks Have Sharp Expressivity Bounds
arXiv:2607. 19042v1 Announce Type: cross Abstract: Neural hypergraphs are a natural generalization of neural networks, the reference models in modern machine learning.
arXiv Machine Learning
Jun 19
Statistical Properties of Training & Generalization
arXiv:2606. 20299v1 Announce Type: cross Abstract: Deep learning has managed to evade numerous intuitions from classical statistics to achieve unprecedented performance on a number of real-world tasks.
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.
arXiv Machine Learning
Jun 26
Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy
arXiv:2606. 26873v1 Announce Type: cross Abstract: Graphs provide a natural language for relational data in chemistry, biology and optimisation.
arXiv Machine Learning
Aug 20
Quantum Tensor Network Learning with DMRG
The paper introduces a quantum tensor network learning framework that employs matrix product states (MPS) as a machine‑learning architecture, adding a global normalization condition to interpret the MPS as a quantum state. It compares two optimization strategies—gradient descent and a DMRG‑adapted method—to identify locally optimal tensors and evaluates their effectiveness.
arXiv Machine Learning
Sep 1
Graph Representational Learning: When Does More Expressivity Hurt Generalization?
arXiv:2505.11298v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive per...