paper-with-me

홈 › Papers

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory

2025-10-14 · Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.12077

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

Minimum Description Length and Generalization Guarantees for Representation Learning

2024-02-05 · NeurIPS 2023 11 · Milad Sefidgaran, Abdellatif Zaidi, Piotr Krasnowski

A major challenge in designing efficient statistical supervised learning algorithms is finding representations that perform well not only on available training samples but also on unseen data. While the study of represen…

Generalization BoundsRepresentation Learning

From Mechanistic to Compositional Interpretability

2026-05-09 · Ward Gauderis, Thomas Dooms, Steven T. Homer, Kola Ayonrinde 외 arxiv

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanatio…

A Geometric Modeling of Occam's Razor in Deep Learning

2019-05-27 · Ke Sun, Frank Nielsen

Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs stunning performances in practice is all the more intriguing and not explainable using the stan…

Deep LearningModel Selection

Bivariate Causal Discovery Using Rate-Distortion MDL: An Information Dimension Approach

2026-04-07 · Tiago Brogueira, Mário A. T. Figueiredo arxiv

Approaches to bivariate causal discovery based on the minimum description length (MDL) principle approximate the (uncomputable) Kolmogorov complexity of the models in each causal direction, selecting the one with the low…

Density Estimation

Evaluating representations by the complexity of learning low-loss predictors

2020-09-15 · William F. Whitney, Min Jae Song, David Brandfonbrener, Jaan Altosaar 외

We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representa…