تقرير
Towards Healing the Blindness of Score Matching
العنوان: | Towards Healing the Blindness of Score Matching |
---|---|
المؤلفون: | Zhang, Mingtian, Key, Oscar, Hayes, Peter, Barber, David, Paige, Brooks, Briol, François-Xavier |
سنة النشر: | 2022 |
المجموعة: | Computer Science Statistics |
مصطلحات موضوعية: | Statistics - Machine Learning, Computer Science - Machine Learning |
الوصف: | Score-based divergences have been widely used in machine learning and statistics applications. Despite their empirical success, a blindness problem has been observed when using these for multi-modal distributions. In this work, we discuss the blindness problem and propose a new family of divergences that can mitigate the blindness problem. We illustrate our proposed divergence in the context of density estimation and report improved performance compared to traditional approaches. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2209.07396 |
رقم الأكسشن: | edsarx.2209.07396 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |