activity
20122026
most citedLimits of Private Learning with Access to Public Data

15 citations · 99 across the 45 of their papers we have counts for

collaborators
Showing 2022 · cs.LGShow all

8 papers · 2 filters

cs.LG2022

Differentially-Private Bayes Consistency

Olivier Bousquet, Haim Kaplan, Aryeh Kontorovich +4

We construct a universally Bayes consistent learning rule that satisfies differential privacy (DP). We first handle the setting of binary classification and then extend our rule to…

cs.LG2022

On Optimal Learning Under Targeted Data Poisoning

Steve Hanneke, Amin Karbasi, Mohammad Mahmoody +2

Consider the task of learning a hypothesis class in the presence of an adversary that can replace up to an fraction of the examples in the training set with arbit…

cs.LG2022

Fine-Grained Distribution-Dependent Learning Curves

Olivier Bousquet, Steve Hanneke, Shay Moran +2

Learning curves plot the expected error of a learning algorithm as a function of the number of labeled samples it receives from a target distribution. They are widely used as a mea…

cs.LG2022

Understanding Generalization via Leave-One-Out Conditional Mutual Information

Mahdi Haghifam, Shay Moran, Daniel M. Roy +1

We study the mutual information between (certain summaries of) the output of a learning algorithm and its training data, conditional on a supersample of i.i.d. data from…

cs.LG2022★ 1 cited

A Resilient Distributed Boosting Algorithm

Yuval Filmus, Idan Mehalel, Shay Moran

Given a learning task where the data is distributed among several parties, communication is one of the fundamental resources which the parties would like to minimize. We present a…

cs.LG2022★ 1 cited

Active Learning with Label Comparisons

Gal Yona, Shay Moran, Gal Elidan +1

Supervised learning typically relies on manual annotation of the true labels. When there are many potential classes, searching for the best one can be prohibitive for a human annot…