From the 1 of 12 linked papers with an AI index.
12 papers
Confidence Horizons
Chase Mathis, Ian Waudby-Smith
Anytime-valid inference enables analysts to continuously monitor their data and stop experiments early. However, the majority of these methods incur a certain conservativeness by r…
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
Keegan Harris, Brian W. Lee, Ian Waudby-Smith +3
The paper introduces a game‑theoretic framework for RL fine‑tuning that determines the KL regularization coefficient by treating the trade‑off between reward and deviation from a r…
Gaffke's confidence interval for the mean of bounded data is inadmissible but asymptotically efficient
Jiahao Ming, Aaditya Ramdas, Yi Shen +2
Given observations , Gaffke (2005) defined \[ K_n(\mathbf x)=\mathbb{P}_{\mathbf D}\!\left\{\sum_{i=1}^n x_iD_i\le 1\right\}, \qquad (D_0,D_1,\ldots,D_n)…
Multi-Armed Sequential Hypothesis Testing by Betting
Ricardo J. Sandoval, Ian Waudby-Smith, Michael I. Jordan
We consider a variant of sequential testing by betting where, at each time step, the statistician is presented with multiple data sources (arms) and obtains data by choosing one of…
Combining e-values using demi-supermartingales
Jiahao Ming, Yi Shen, Aaditya Ramdas +2
We present a new method for combining e-variables through demi-supermartingales, which settles an old conjecture in the literature on nonparametric mean testing. It also provides a…
Post-Hoc Large-Sample Statistical Inference
Ben Chugg, Etienne Gauthier, Michael I. Jordan +2
We derive inferential procedures for large sample sizes that remain valid under data-dependent significance levels (so-called "post-hoc valid inference"). Classical statistical too…