.png){kind=icon}
.png){kind=icon}
Return
Vanishing boosted weights: A consistent algorithm to learn interpretable rules
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2021.08.016.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 intro-duce 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, Cor-rective 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 com-pared to the state-of-the-art methods, and outperform them. (c) 2021 Elsevier B.V. All rights reserved.
Keywords:
Machine learning
Fine-tuning procedure
Interpretable sparse models
Decision stumps
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.