The Power of Comparisons for Actively Learning Linear Classifiers

07/08/2019
by   Max Hopkins, et al.
4

In the world of big data, large but costly to label datasets dominate many fields. Active learning, an unsupervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts with exponentially fewer labeled samples. While previous results show that active learning performs no better than its supervised alternative for important concept classes such as linear separators, we show that by adding weak distributional assumptions and allowing comparison queries, active learning requires exponentially fewer samples. Further, we show that these results hold as well for a stronger model of learning called Reliable and Probably Useful (RPU) learning. In this model, our learner is not allowed to make mistakes, but may instead answer "I don't know." While previous negative results showed this model to have intractably large sample complexity for label queries, we show that comparison queries make RPU-learning at worst logarithmically more expensive in the passive case, and quadratically more expensive in the active case.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/10/2022

Active Learning with Label Comparisons

Supervised learning typically relies on manual annotation of the true la...
research
05/07/2018

Efficient active learning of sparse halfspaces

We study the problem of efficient PAC active learning of homogeneous lin...
research
03/31/2022

Efficient Active Learning with Abstention

The goal of active learning is to achieve the same accuracy achievable b...
research
09/08/2022

Active Learning of Classifiers with Label and Seed Queries

We study exact active learning of binary and multiclass classifiers with...
research
02/22/2021

Nonparametric adaptive active learning under local smoothness condition

Active learning is typically used to label data, when the labeling proce...
research
11/06/2015

Active Perceptual Similarity Modeling with Auxiliary Information

Learning a model of perceptual similarity from a collection of objects i...
research
08/08/2018

Affect Estimation in 3D Space Using Multi-Task Active Learning for Regression

Acquisition of labeled training samples for affective computing is usual...

Please sign up or login with your details

Forgot password? Click here to reset