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.
arXiv preprint arXiv:2005.11818 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
A hypothesis class is learnable in this online precision-recall feedback model if and only if it has finite VC dimension, with algorithms achieving regret bounds in realizable and agnostic settings despite ERM failing.
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.
-
Online Set Learning from Precision and Recall Feedback
A hypothesis class is learnable in this online precision-recall feedback model if and only if it has finite VC dimension, with algorithms achieving regret bounds in realizable and agnostic settings despite ERM failing.