English

Making Learners (More) Monotone

Machine Learning 2019-11-26 v1 Machine Learning

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\text{MT}_{\text{HT}} makes less than 1%1\% non-monotone decisions on MNIST while staying competitive in terms of error rate compared to several baselines.

Keywords

Cite

@article{arxiv.1911.11030,
  title  = {Making Learners (More) Monotone},
  author = {Tom J. Viering and Alexander Mey and Marco Loog},
  journal= {arXiv preprint arXiv:1911.11030},
  year   = {2019}
}
R2 v1 2026-06-23T12:26:36.498Z