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.
(1975); A Theory of Program Size Formally Identical to Information Theory, Journal of the Association for Computing Machinery 22:3, pp
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
Evidence-tracked tape semantics yields a higher-order logic for randomized programs in which entailments are witnessed by uniform evidence transformers and quantitative probabilities arise by interpretation under a chosen tape measure.
Revives Chaitin's heuristic principle to the extent permitted by logic and shows that Omega cannot be a halting probability under any infinite discrete measure, proposing alternative definitions instead.
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.
-
Evidence-Tracked Tape Semantics for Probabilistic Computation
Evidence-tracked tape semantics yields a higher-order logic for randomized programs in which entailments are witnessed by uniform evidence transformers and quantitative probabilities arise by interpretation under a chosen tape measure.
-
On Chaitin's Heuristic Principle and Halting Probability
Revives Chaitin's heuristic principle to the extent permitted by logic and shows that Omega cannot be a halting probability under any infinite discrete measure, proposing alternative definitions instead.