Convergence of Uncertainty Sampling for Active Learning

by   Anant Raj, et al.

Uncertainty sampling in active learning is heavily used in practice to reduce the annotation cost. However, there has been no wide consensus on the function to be used for uncertainty estimation in binary classification tasks and convergence guarantees of the corresponding active learning algorithms are not well understood. The situation is even more challenging for multi-category classification. In this work, we propose an efficient uncertainty estimator for binary classification which we also extend to multiple classes, and provide a non-asymptotic rate of convergence for our uncertainty sampling-based active learning algorithm in both cases under no-noise conditions (i.e., linearly separable data). We also extend our analysis to the noisy case and provide theoretical guarantees for our algorithm under the influence of noise in the task of binary and multi-class classification.



There are no comments yet.


page 1

page 2

page 3

page 4


Discriminative Active Learning

We propose a new batch mode active learning algorithm designed for neura...

On the Relationship between Data Efficiency and Error for Uncertainty Sampling

While active learning offers potential cost savings, the actual data eff...

A quantum active learning algorithm for sampling against adversarial attacks

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

Convergence Rates of Active Learning for Maximum Likelihood Estimation

An active learner is given a class of models, a large set of unlabeled e...

Geometry in Active Learning for Binary and Multi-class Image Segmentation

We propose an Active Learning approach to image segmentation that exploi...

Let Me At Least Learn What You Really Like: Dealing With Noisy Humans When Learning Preferences

Learning the preferences of a human improves the quality of the interact...

A New Perspective on Pool-Based Active Classification and False-Discovery Control

In many scientific settings there is a need for adaptive experimental de...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.