Library
home (Home) TU Delft Repository login Login

Making Learners (More) Monotone

Conference Paper (2020)
Author(s)

Tom Julian Viering (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Alexander Mey (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Marco Loog (University of Copenhagen, TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Pattern Recognition and Bioinformatics
DOI related publication
https://doi.org/10.1007/978-3-030-44584-3_42 Final published version
More Info
expand_more
Publication Year
2020
Language
English
Research Group
Pattern Recognition and Bioinformatics
Bibliographical Note
Virtual/online event due to COVID-19
Volume number
12080
Pages (from-to)
535-547
ISBN (print)
978-3-030-44583-6
ISBN (electronic)
978-3-030-44584-3
Event
18th International Conference on Intelligent Data Analysis, IDA 2020 (2020-04-27 - 2020-04-29), Konstanz, Germany
Downloads counter
290
Collections
Institutional Repository
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Learning performance can show non-monotonic behavior. That is, more data does not necessarily lead to better models, even on average. We propose three algorithms that take a supervised learning model and make it perform more monotone. We prove consistency and monotonicity with high probability, and evaluate the algorithms on scenarios where non-monotone behaviour occurs. Our proposed algorithm MTHT makes less than 1% non-monotone decisions on MNIST while staying competitive in terms of error rate compared to several baselines. Our code is available at https://github.com/tomviering/monotone.