research
∙
03/20/2023
What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement
The question of what makes a data distribution suitable for deep learnin...
share
research
∙
11/29/2022
On the Ability of Graph Neural Networks to Model Interactions Between Vertices
Graph neural networks (GNNs) are widely used for modeling complex intera...
research
∙
01/27/2022
Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks
In the pursuit of explaining implicit regularization in deep learning, p...
research
∙
02/19/2021
Implicit Regularization in Tensor Factorization
Implicit regularization in deep learning is perceived as a tendency of g...
research
∙
09/25/2020
RecoBERT: A Catalog Language Model for Text-Based Recommendations
Language models that utilize extensive self-supervised pre-training from...
research
∙
05/13/2020
Implicit Regularization in Deep Learning May Not Be Explainable by Norms
Mathematically characterizing the implicit regularization induced by gra...
research
∙
08/14/2019