4 papers
How Many Repeated Pairwise Comparisons Are Needed for Ranking under Heterogeneity?
Shashaank Aiyer, Han Shao
We study ranking models by population-average utility from pairwise comparisons when preferences vary across users and tasks. Prior work shows that a single comparison per user can…
Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale
Shashaank Aiyer, Yishay Mansour, Shay Moran +2
We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability. Our main result establishes a scale-sensitive generalization of the f…
A Theoretical Framework for Statistical Evaluability of Generative Models
Shashaank Aiyer, Yishay Mansour, Shay Moran +1
Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth distribution. In supervised learning…
Active Learning via Regression Beyond Realizability
Atul Ganju, Shashaank Aiyer, Ved Sriraman +1
We present a new active learning framework for multiclass classification based on surrogate risk minimization that operates beyond the standard realizability assumption. Existing s…