End-to-end sample complexity for autoregressive generators can realize any scaling rate r(T) between constant and linear, while chain-of-thought supervision eliminates all dependence on T.
Cot information: Improved sam- ple complexity under chain-of-thought supervision.arXiv preprint arXiv:2505.15927
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Online mistake bounds for autoregressive output learning can grow logarithmically with generation horizon M under end-to-end feedback but become independent of M with chain-of-thought trajectory access.
citing papers explorer
-
Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
End-to-end sample complexity for autoregressive generators can realize any scaling rate r(T) between constant and linear, while chain-of-thought supervision eliminates all dependence on T.
-
A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
Online mistake bounds for autoregressive output learning can grow logarithmically with generation horizon M under end-to-end feedback but become independent of M with chain-of-thought trajectory access.