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.
@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}
}