arXiv (All)
open access
Information-Theoretic Analysis of Next-Token Prediction under Markovian Data
We develop an information-theoretic framework for generalization in next-token prediction under temporally dependent data. We consider independent trajectories generated by finite-memory Markov processes and distinguish algorithmic dependence, quantified by mutual information, from temporal dependen
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Probabilistic inferences from conjoined to iterated conditionals#765216
- Composable Decoding on the Probability Simplex: Theory and Implementation#1129596
- Large Language Models Develop Belief State Geometry In-Context#1123741
- Large Language Models Develop Belief State Geometry In-Context#919385
- Entropy and Fisher information in non-convex domains: one chain to rule them all#1012088
Record · ID 1128989
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive