Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy

by   Maria-Florina Balcan, et al.

We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random examples. It builds on the powerful statistical query framework of Kearns (1993). We show that any efficient active statistical learning algorithm can be automatically converted to an efficient active learning algorithm which is tolerant to random classification noise as well as other forms of "uncorrelated" noise. The complexity of the resulting algorithms has information-theoretically optimal quadratic dependence on 1/(1-2η), where η is the noise rate. We show that commonly studied concept classes including thresholds, rectangles, and linear separators can be efficiently actively learned in our framework. These results combined with our generic conversion lead to the first computationally-efficient algorithms for actively learning some of these concept classes in the presence of random classification noise that provide exponential improvement in the dependence on the error ϵ over their passive counterparts. In addition, we show that our algorithms can be automatically converted to efficient active differentially-private algorithms. This leads to the first differentially-private active learning algorithms with exponential label savings over the passive case.


page 1

page 2

page 3

page 4


The Power of Localization for Efficiently Learning Linear Separators with Noise

We introduce a new approach for designing computationally efficient lear...

Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning

The Private Aggregation of Teacher Ensembles (PATE) framework is one of ...

Diameter-based Interactive Structure Search

In this work, we introduce interactive structure search, a generic frame...

Neural Active Learning on Heteroskedastic Distributions

Models that can actively seek out the best quality training data hold th...

A quantum active learning algorithm for sampling against adversarial attacks

Adversarial attacks represent a serious menace for learning algorithms a...

Noise-tolerant, Reliable Active Classification with Comparison Queries

With the explosion of massive, widely available unlabeled data in the pa...

Active Learning for Undirected Graphical Model Selection

This paper studies graphical model selection, i.e., the problem of estim...

Please sign up or login with your details

Forgot password? Click here to reset