Private Sequential Learning

05/06/2018
by   John N. Tsitsiklis, et al.
0

We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, v^*, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes the learner's queries, though not the responses, and tries to infer from them the value of v^*. The objective of the learner is to obtain an accurate estimate of v^* using only a small number of queries, while simultaneously protecting her privacy by making v^* provably difficult to learn for the adversary. Our main results provide tight upper and lower bounds on the learner's query complexity as a function of desired levels of privacy and estimation accuracy. We also construct explicit query strategies whose complexity is optimal up to an additive constant.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/21/2019

Optimal query complexity for private sequential learning

Motivated by privacy concerns in many practical applications such as Fed...
research
11/15/2019

Query Complexity of Bayesian Private Learning

We study the query complexity of Bayesian Private Learning: a learner wi...
research
02/23/2021

Learner-Private Online Convex Optimization

Online convex optimization is a framework where a learner sequentially q...
research
02/10/2020

Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers

We consider the problem of prediction by a machine learning algorithm, c...
research
10/30/2019

Dynamically Protecting Privacy, under Uncertainty

We propose and analyze the ε-Noisy Goal Prediction Game to study a funda...
research
11/17/2019

Learning Query Inseparable ELH Ontologies

We investigate the complexity of learning query inseparable ontologies ...
research
02/21/2018

Data Privacy for a ρ-Recoverable Function

A user's data is represented by a finite-valued random variable. Given a...

Please sign up or login with your details

Forgot password? Click here to reset