DeepAI AI Chat
Log In Sign Up

Privately Answering Classification Queries in the Agnostic PAC Model

07/31/2019
by   Raef Bassily, et al.
0

We revisit the problem of differentially private release of classification queries. In this problem, the goal is to design an algorithm that can accurately answer a sequence of classification queries based on a private training set while ensuring differential privacy. We formally study this problem in the agnostic PAC model and derive a new upper bound on the private sample complexity. Our results improve over those obtained in a recent work [BTT18] for the agnostic PAC setting. In particular, we give an improved construction that yields a tighter upper bound on the sample complexity. Moreover, unlike [BTT18], our accuracy guarantee does not involve any blow-up in the approximation error associated with the given hypothesis class. Given any hypothesis class with VC-dimension d, we show that our construction can privately answer up to m classification queries with average excess error α using a private sample of size ≈d/α^2(1, √(m)α^3/2). Using recent results on private learning with auxiliary public data, we extend our construction to show that one can privately answer any number of classification queries with average excess error α using a private sample of size ≈d/α^2(1, √(d)α). Our results imply that when α is sufficiently small (high-accuracy regime), the private sample size is essentially the same as the non-private sample complexity of agnostic PAC learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/23/2020

Private Query Release Assisted by Public Data

We study the problem of differentially private query release assisted by...
02/04/2020

Efficient, Noise-Tolerant, and Private Learning via Boosting

We introduce a simple framework for designing private boosting algorithm...
03/14/2018

Model-Agnostic Private Learning via Stability

We design differentially private learning algorithms that are agnostic t...
03/10/2020

Closure Properties for Private Classification and Online Prediction

Let H be a class of boolean functions and consider acomposed class H' th...
05/16/2023

Private Everlasting Prediction

A private learner is trained on a sample of labeled points and generates...
10/25/2019

Limits of Private Learning with Access to Public Data

We consider learning problems where the training set consists of two typ...
11/16/2022

Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes

In many learning theory problems, a central role is played by a hypothes...