1 citations · 2 across the 12 of their papers we have counts for
3 papers · 1 filter
Measuring in-context algorithmic reasoning in language models against an exact Bayes-optimal reference
Luan Ozelim, Hector Zenil
Whether large language models perform algorithmic inference or pattern completion is hard to test, because most benchmarks supply answers but no distributional reference for what t…
Algorithmic Information Dynamics of Learning: A Certified, Differentiable Complexity Controller for Grokking
Luan Ozelim, Hector Zenil, Abicumaran Uthamacumaran
Algorithmic Information Dynamics (AID) studies systems by perturbing them and measuring changes in algorithmic complexity, but its usual estimator, the Block Decomposition Method,…
Binarized Neural Networks Converge Toward Algorithmic Simplicity: Empirical Support for the Learning-as-Compression Hypothesis
Eduardo Y. Sakabe, Felipe S. Abrahão, Alexandre Simões +4
Understanding and controlling the informational complexity of neural networks is a central challenge in machine learning, with implications for generalization, optimization, and mo…