تقرير
Top-$k$ Classification and Cardinality-Aware Prediction
العنوان: | Top-$k$ Classification and Cardinality-Aware Prediction |
---|---|
المؤلفون: | Mao, Anqi, Mohri, Mehryar, Zhong, Yutao |
سنة النشر: | 2024 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Computer Science - Machine Learning, Statistics - Machine Learning |
الوصف: | We present a detailed study of top-$k$ classification, the task of predicting the $k$ most probable classes for an input, extending beyond single-class prediction. We demonstrate that several prevalent surrogate loss functions in multi-class classification, such as comp-sum and constrained losses, are supported by $H$-consistency bounds with respect to the top-$k$ loss. These bounds guarantee consistency in relation to the hypothesis set $H$, providing stronger guarantees than Bayes-consistency due to their non-asymptotic and hypothesis-set specific nature. To address the trade-off between accuracy and cardinality $k$, we further introduce cardinality-aware loss functions through instance-dependent cost-sensitive learning. For these functions, we derive cost-sensitive comp-sum and constrained surrogate losses, establishing their $H$-consistency bounds and Bayes-consistency. Minimizing these losses leads to new cardinality-aware algorithms for top-$k$ classification. We report the results of extensive experiments on CIFAR-100, ImageNet, CIFAR-10, and SVHN datasets demonstrating the effectiveness and benefit of these algorithms. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2403.19625 |
رقم الأكسشن: | edsarx.2403.19625 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |