2 citations · 2 across the 4 of their papers we have counts for
3 papers · 1 filter
What Can Language Models Inherit from Solomonoff Induction? Limits, Attainable Properties, and What Served Conditionals Reveal
Luan Ozelim, Abicumaran Uthamacumaran, Hector Zenil
A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them closer to Solomonoff induction,…
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,…