10 papers
Improved Distribution Estimation in
Doron Cohen, Aryeh Kontorovich, Yonatan Livshitz
We present improved bounds for estimating discrete probability distributions under the norm. These include minimax bounds in expectation and high-probability tail bou…
Realizable Bayes-Consistency for General Metric Losses
Dan Tsir Cohen, Steve Hanneke, Aryeh Kontorovich
We study strong universal Bayes-consistency in the realizable setting for learning with general metric losses, extending classical characterizations beyond - classification (…
A Fine-Grained Understanding of Uniform Convergence for Halfspaces
Aryeh Kontorovich, Kasper Green Larsen
We study the fine-grained uniform convergence behavior of halfspaces beyond worst-case VC bounds. For inhomogeneous halfspaces in with , we show that standar…
A homogenization principle for total variation
Aryeh Kontorovich
A homogenization principle for total variation We prove an inequality comparing the variational distance between pairs of product probability measures to its homogenized counterpar…
TV over Bernoulli products: the small parameter regime
Ariel Avital, Aryeh Kontorovich, George Salafatinos
We study the total variation distance (TV) between two -fold Bernoulli product measures parametrized by and , respectively, in…
TV homogenization inequalities
Aryeh Kontorovich
We study the total variation distance under two information-erasing maps on inhomogeneous Bernoulli product measures: summation and homogenization. While summation is a Markov kern…