Found 2 document(s)
Page 1 of 1
-
Strict replicability requires two independent training samples, processed with the same random seed, to produce exactly the same hypothesis. We study realizable Boolean learning under unknown and known instance marginals...
-
Pointwise replicability asks that two independently trained predictors, using the same random seed, agree at each fixed query with high probability. We determine its optimal agnostic sample complexity on finite and count...