Log In Sign Up

Closure Properties for Private Classification and Online Prediction

by   Noga Alon, et al.

Let H be a class of boolean functions and consider acomposed class H' that is derived from H using some arbitrary aggregation rule (for example, H' may be the class of all 3-wise majority votes of functions in H). We upper bound the Littlestone dimension of H' in terms of that of H. The bounds are proved using combinatorial arguments that exploit a connection between the Littlestone dimension and Thresholds. As a corollary, we derive closure properties for online learning and private PAC learning. The derived bounds on the Littlestone dimension exhibit an undesirable super-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 H to a private learner for the composed class H'. Using the same ideas we show that any (proper or improper) private algorithm that learns a class of functions H 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 H in the agnostic case.


page 1

page 2

page 3

page 4


Multiclass versus Binary Differentially Private PAC Learning

We show a generic reduction from multiclass differentially private PAC l...

Privately Answering Classification Queries in the Agnostic PAC Model

We revisit the problem of differentially private release of classificati...

Private Query Release Assisted by Public Data

We study the problem of differentially private query release assisted by...

Near-tight closure bounds for Littlestone and threshold dimensions

We study closure properties for the Littlestone and threshold dimensions...

Model-Agnostic Private Learning via Stability

We design differentially private learning algorithms that are agnostic t...

Littlestone Classes are Privately Online Learnable

We consider the problem of online classification under a privacy constra...

PAC learning with stable and private predictions

We study binary classification algorithms for which the prediction on an...