Nuances in Margin Conditions Determine Gains in Active Learning

10/16/2021
by   Samory Kpotufe, et al.
0

We consider nonparametric classification with smooth regression functions, where it is well known that notions of margin in E[Y|X] determine fast or slow rates in both active and passive learning. Here we elucidate a striking distinction between the two settings. Namely, we show that some seemingly benign nuances in notions of margin – involving the uniqueness of the Bayes classifier, and which have no apparent effect on rates in passive learning – determine whether or not any active learner can outperform passive learning rates. In particular, for Audibert-Tsybakov's margin condition (allowing general situations with non-unique Bayes classifiers), no active learner can gain over passive learning in commonly studied settings where the marginal on X is near uniform. Our results thus negate the usual intuition from past literature that active rates should improve over passive rates in nonparametric settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/16/2017

Adaptivity to Noise Parameters in Nonparametric Active Learning

This work addresses various open questions in the theory of active learn...
research
06/03/2022

Indirect Active Learning

Traditional models of active learning assume a learner can directly mani...
research
02/08/2019

K-nn active learning under local smoothness condition

There is a large body of work on convergence rates either in passive or ...
research
12/01/2022

Uniform versus uncertainty sampling: When being active is less efficient than staying passive

It is widely believed that given the same labeling budget, active learni...
research
05/15/2015

An Analysis of Active Learning With Uniform Feature Noise

In active learning, the user sequentially chooses values for feature X a...
research
10/22/2014

Active Regression by Stratification

We propose a new active learning algorithm for parametric linear regress...
research
07/24/2020

Opacity of Discrete Event Systems with Active Intruder

Opacity is a security property formalizing the information leakage of a ...

Please sign up or login with your details

Forgot password? Click here to reset