تقرير
Shift Happens: Adjusting Classifiers
| العنوان: | Shift Happens: Adjusting Classifiers |
|---|---|
| المؤلفون: | Heiser, Theodore James Thibault, Allikivi, Mari-Liis, Kull, Meelis |
| المصدر: | ECML PKDD 2019. Lecture Notes in Computer Science, vol 11907. Springer, Cham (2020) |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning |
| الوصف: | Minimizing expected loss measured by a proper scoring rule, such as Brier score or log-loss (cross-entropy), is a common objective while training a probabilistic classifier. If the data have experienced dataset shift where the class distributions change post-training, then often the model's performance will decrease, over-estimating the probabilities of some classes while under-estimating the others on average. We propose unbounded and bounded general adjustment (UGA and BGA) methods that transform all predictions to (re-)equalize the average prediction and the class distribution. These methods act differently depending on which proper scoring rule is to be minimized, and we have a theoretical guarantee of reducing loss on test data, if the exact class distribution is known. We also demonstrate experimentally that, when in practice the class distribution is known only approximately, there is often still a reduction in loss depending on the amount of shift and the precision to which the class distribution is known. Comment: ECML PKDD 2019 conference paper, 16 pages |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1007/978-3-030-46147-8_4 |
| URL الوصول: | http://arxiv.org/abs/2111.02529 |
| رقم الأكسشن: | edsarx.2111.02529 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1007/978-3-030-46147-8_4 |
|---|