You are here

Vanishing boosted weights: a consistent algorithm to learn interpretable rules

TitleVanishing boosted weights: a consistent algorithm to learn interpretable rules
Publication TypeJournal Article
Year of Publication2021
AuthorsSokolovska, N, Behbahani, YMohseni
JournalPattern Recognition Letters
ISSN0167-8655
Abstract

Learning compact but highly accurate models that help in human decision-making is challenging. Most such scoring systems were constructed by human experts using some heuristics. In this contribution, we propose a principled method with theoretical guarantees to learn interpretable simple rules. We introduce Vanishing Boosted Weights (VBW) approach which is a corrective fine-tuning procedure on decision stumps. It is a simple method which surprisingly was never investigated. We propose its extension, Corrective Federated Averaging VBW, that is practical in a federated learning scenario. We illustrate by our numerical experiments both on simulated and real data that the novel approaches are competitive compared to the state-of-the-art methods, and outperform them.

URLhttps://www.sciencedirect.com/science/article/pii/S0167865521003081
DOI10.1016/j.patrec.2021.08.016

Open Positions