تقرير
$\alpha$-Divergence Loss Function for Neural Density Ratio Estimation
العنوان: | $\alpha$-Divergence Loss Function for Neural Density Ratio Estimation |
---|---|
المؤلفون: | Kitazawa, Yoshiaki |
سنة النشر: | 2024 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Statistics - Machine Learning, Computer Science - Machine Learning |
الوصف: | Recently, neural networks have produced state-of-the-art results for density-ratio estimation (DRE), a fundamental technique in machine learning. However, existing methods bear optimization issues that arise from the loss functions of DRE: a large sample requirement of Kullback--Leibler (KL)-divergence, vanishing of train loss gradients, and biased gradients of the loss functions. Thus, an $\alpha$-divergence loss function ($\alpha$-Div) that offers concise implementation and stable optimization is proposed in this paper. Furthermore, technical justifications for the proposed loss function are presented. The stability of the proposed loss function is empirically demonstrated and the estimation accuracy of DRE tasks is investigated. Additionally, this study presents a sample requirement for DRE using the proposed loss function in terms of the upper bound of $L_1$ error, which connects a curse of dimensionality as a common problem in high-dimensional DRE tasks. Comment: $\mathcal{T}_{\text{Lip}}$ in Theorem 7.1 (Theorem B.15.) was changed to the set of all locally Lipschitz continuous functions. In the previous version, $\mathcal{T}_{\text{Lip}}$ was defined as the set of all Lipschitz continuous functions, which is unsuitable for the statement of case (ii) in the theorem |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2402.02041 |
رقم الأكسشن: | edsarx.2402.02041 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |