38 citations · 82 across the 18 of their papers we have counts for
3 papers · 1 filter
Dimensionality reduction, regularization, and generalization in overparameterized regressions
Ningyuan Huang, David W. Hogg, Soledad Villar
Overparameterization in deep learning is powerful: Very large models fit the training data perfectly and yet often generalize well. This realization brought back the study of linea…
A Simple Spectral Failure Mode for Graph Convolutional Networks
Carey E. Priebe, Cencheng Shen, Ningyuan Huang +1
Neural networks have achieved remarkable successes in machine learning tasks. This has recently been extended to graph learning using neural networks. However, there is limited the…
VisualSem: A High-quality Knowledge Graph for Vision and Language
Houda Alberts, Teresa Huang, Yash Deshpande +4
An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge…