3 papers
cs.LG2026
Neural collapse in the orthoplex regime
James Alcala, Rayna Andreeva, Vladimir A. Kobzar +4
When training a neural network for classification, the feature vectors of the training set are known to collapse to the vertices of a regular simplex, provided the dimension of…
cs.LG2026
Curse of Dimensionality in Neural Network Optimization
Sanghoon Na, Haizhao Yang
This paper demonstrates that when a shallow neural network with a Lipschitz continuous activation function is trained using either empirical or population risk to approximate a tar…
cs.LG2024
Frame Quantization of Neural Networks
Wojciech Czaja, Sanghoon Na
We present a post-training quantization algorithm with error estimates relying on ideas originating from frame theory. Specifically, we use first-order Sigma-Delta () quantiz…