2 papers
stat.ML2025
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
Einar Urdshals, Edmund Lau, Jesse Hoogland +2
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through…
cs.LG2025
The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
Maxwell Adam, Zach Furman, Jesse Hoogland
We introduce the loss kernel, an interpretability method for measuring similarity between data points according to a trained neural network. The kernel is the covariance matrix of…