QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
A tutorial introduction to the minimum description length principle
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
This tutorial provides an overview of and introduction to Rissanen's Minimum Description Length (MDL) Principle. The first chapter provides a conceptual, entirely non-technical introduction to the subject. It serves as a basis for the technical introduction given in the second chapter, in which all the ideas of the first chapter are made mathematically precise. The main ideas are discussed in great conceptual and technical detail. This tutorial is an extended version of the first two chapters of the collection "Advances in Minimum Description Length: Theory and Application" (edited by P.Grunwald, I.J. Myung and M. Pitt, to be published by the MIT Press, Spring 2005).
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Context-ReAct enables agents to dynamically manage context via five atomic operations, and LongSeeker fine-tuned on 10k trajectories achieves 61.5% and 62.5% on BrowseComp benchmarks, outperforming prior agents.
Proposes an MDL-based criterion for selecting the latent dimension of linear dynamical systems that accounts for latent structure omitted in prior work.
citing papers explorer
-
Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis
QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
-
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
Context-ReAct enables agents to dynamically manage context via five atomic operations, and LongSeeker fine-tuned on 10k trajectories achieves 61.5% and 62.5% on BrowseComp benchmarks, outperforming prior agents.
-
Inferring Latent dimension of Linear Dynamical System with Minimum Description Length
Proposes an MDL-based criterion for selecting the latent dimension of linear dynamical systems that accounts for latent structure omitted in prior work.