1 citations · 1 across the 2 of their papers we have counts for
4 papers
Aligning the Query Space: Greedy Information Projection for Language Model Data Selection
Victor Ye Dong, Kuan-Yun Lee, Jiamei Shuai +3
Data selection for language models is often framed as balancing example quality and diversity. We argue that both are consequences of a more fundamental principle: selected example…
Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations
Chih-Kuan Yeh, Kuan-Yun Lee, Frederick Liu +1
A popular explainable AI (XAI) approach to quantify feature importance of a given model is via Shapley values. These Shapley values arose in cooperative games, and hence a critical…
Linear Models are Most Favorable among Generalized Linear Models
Kuan-Yun Lee, Thomas A. Courtade
We establish a nonasymptotic lower bound on the minimax risk for a class of generalized linear models. It is further shown that the minimax risk for the canonical linear mode…
A Family of Bayesian Cramér-Rao Bounds, and Consequences for Log-Concave Priors
Efe Aras, Kuan-Yun Lee, Ashwin Pananjady +1
Under minimal regularity assumptions, we establish a family of information-theoretic Bayesian Cramér-Rao bounds, indexed by probability measures that satisfy a logarithmic Sobolev…