题    目：Optimal Mixture-of-Experts Model Averaging for Conditional Generative Learning

嘉　宾：贺百花 副教授 中国科学技术大学

主持人：曾智宇 助理教授 上海交通大学安泰经济与管理学院

时　间：2026年4月9日（周四）14:00-15:30

地　点：安泰楼A507室

内容简介：

Learning complex conditioned distributions is essential in modern generative modeling, powering applications from probabilistic prediction to AI-driven image and text synthesis. Different generative models often excel on some conditioning inputs but struggle on others, yet classical ensemble methods assign fixed weights that ignore this variability. We introduce a statistically principled Optimal Mixture-of-Experts framework that learns input-dependent weights to combine multiple conditional generators dynamically. By extending model averaging theory and using integral probability metrics to align distributions, we prove our adaptive weighting achieves asymptotic optimality under broad conditions. The proposed method can seamlessly incorporate any conditional generator, and can be extended to other probabilistic tasks. Comprehensive simulations and real-world experiments demonstrate that our method consistently outperforms individual models and traditional ensembles. These experiments, such as image generation and demand distribution learning, show its broad effectiveness in other statisitic and AI applications.

演讲人简介：

贺百花,中国科学技术大学特任副教授,主要从事模型平均以及多源域学习等领域的研究,相关论文发表在JASA,JMLR,IJOC等统计和机器学习期刊,主持青年基金以及参与国家自然科学基金重大项目以及科技部重点研发计划,入选省部级人才计划支持.

欢迎广大师生参加！