2 papers
cs.LG2025
New Statistical and Computational Results for Learning Junta Distributions
Lorenzo Beretta
We study the problem of learning junta distributions on , where a distribution is a -junta if its probability mass function depends on a subset of at most variab…
cs.LG2025
Feature Selection and Junta Testing are Statistically Equivalent
Lorenzo Beretta, Nathaniel Harms, Caleb Koch
For a function , the junta testing problem asks whether depends on only variables. If depends on only variables, the feature selecti…