Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise

06/11/2019
by   Henry W J Reeve, et al.
0

We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities. In this setting, identifiability conditions are known, but additional assumptions were shown to be required for finite sample rates, and so far only the parametric rate has been obtained. Assuming these identifiability conditions, together with a measure-smoothness condition on the regression function and Tsybakov's margin condition, we show that the Robust kNN classifier of Gao et al. attains, the minimax optimal rates of the noise-free setting, up to a log factor, even when trained on data with unknown asymmetric label noise. Hence, our results provide a solid theoretical backing for this empirically successful algorithm. By contrast the standard kNN is not even consistent in the setting of asymmetric label noise. A key idea in our analysis is a simple kNN based method for estimating the maximum of a function that requires far less assumptions than existing mode estimators do, and which may be of independent interest for noise proportion estimation and randomised optimisation problems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/14/2019

Classification with unknown class conditional label noise on non-compact feature spaces

We investigate the problem of classification in the presence of unknown ...
research
03/05/2013

Classification with Asymmetric Label Noise: Consistency and Maximal Denoising

In many real-world classification problems, the labels of training examp...
research
07/25/2022

Optimal Convergence Rates of Deep Neural Networks in a Classification Setting

We establish optimal convergence rates up to a log-factor for a class of...
research
04/19/2023

Support and distribution inference from noisy data

We consider noisy observations of a distribution with unknown support. I...
research
09/26/2013

Boosting in the presence of label noise

Boosting is known to be sensitive to label noise. We studied two approac...
research
05/04/2022

Estimation of Standard Auction Models

We provide efficient estimation methods for first- and second-price auct...
research
10/28/2019

Fast classification rates without standard margin assumptions

We consider the classical problem of learning rates for classes with fin...

Please sign up or login with your details

Forgot password? Click here to reset