Showing cs.LGShow all
2 papers · 1 filter
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…