3 papers
cs.LG2026
Fisher information and the geometry of memorization in neural networks
Daniel T. Bernstein, Chase Goddard, Luca Di Carlo +2
A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from idiosyncratic or even corrupte…
cs.LG2026
Soft Quantization: Model Compression Via Weight Coupling
Daniel T. Bernstein, Luca Di Carlo, David Schwab
We show that introducing short-range attractive couplings between the weights of a neural network during training provides a novel avenue for model quantization. These couplings ra…
cs.LG2025
Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
Luca Di Carlo, Chase Goddard, David J. Schwab
Modern neural networks exhibit a striking property: basins of attraction in the loss landscape are often connected by low-loss paths, yet optimization dynamics generally remain con…