Back to Search Start Over

Closure Properties for Private Classification and Online Prediction

Closure Properties for Private Classification and Online Prediction

Authors :
Alon, Noga
Beimel, Amos
Moran, Shay
Stemmer, Uri
Publication Year :
2020

Abstract

Let~$\cH$ be a class of boolean functions and consider a {\it composed class} $\cH'$ that is derived from~$\cH$ using some arbitrary aggregation rule (for example, $\cH'$ may be the class of all 3-wise majority-votes of functions in $\cH$). We upper bound the Littlestone dimension of~$\cH'$ in terms of that of~$\cH$. As a corollary, we derive closure properties for online learning and private PAC learning. The derived bounds on the Littlestone dimension exhibit an undesirable exponential dependence. For private learning, we prove close to optimal bounds that circumvents this suboptimal dependency. The improved bounds on the sample complexity of private learning are derived algorithmically via transforming a private learner for the original class $\cH$ to a private learner for the composed class~$\cH'$. Using the same ideas we show that any ({\em proper or improper}) private algorithm that learns a class of functions $\cH$ in the realizable case (i.e., when the examples are labeled by some function in the class) can be transformed to a private algorithm that learns the class $\cH$ in the agnostic case.<br />Comment: Improved some of the upper bounds w.r.t the Littlestone dimension. Most significantly, we removed two exponents from the bound w.r.t general composition (now it has a single exponent rather than triple exponents). Add a figure. Other

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2003.04509
Document Type :
Working Paper