4 papers · 1 filter
Pessimistic Meta-Induction and Its Limits: Lessons from Frequentist Statistics and Machine Learning Theory
Hanti Lin
This paper challenges the pessimistic meta-inductive argument against scientific realism by undermining its inductive step rather than its historical premise. Although related chal…
Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception
Hanti Lin
Language models are compared by their held-out per-token cross-entropy risk---the quantity scaling laws are fitted to. We show that it cannot be consistently estimated. Consistency…
Meager Success: A Theory of the Unlearnable for Hypothesis Testing
Hanti Lin
When the standard of pointwise consistency for statistical inference -- convergence to the truth in every possible state of the world -- is provably unachievable, the usual respons…
Never Too LATE: A Fully Stochastic Update to the Potential Outcome Framework
Hanti Lin
In the classic potential outcome framework, the local average treatment effect (LATE) and its identification via an instrumental variable are stated in a deterministic setting at t…