Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_ml 50% Match 2 weeks ago

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory

uncategorized › parse-error
📄 Abstract

Abstract: 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 extensive experiments on the Pythia suite with quantization, factorization, and other compression techniques, we find that complexity estimates based on the local learning coefficient (LLC) are closely, and in some cases, linearly correlated with compressibility. Our results provide a path toward rigorously evaluating the limits of model compression.

Key Contributions

JSON parse error: Unexpected token s in JSON at position 29506