报告人：李映真

报告题目：Bayesian Deep Learning

报告摘要：As AI and deep learning methods are getting applied to applications related to decision making, reliability of the deep neural networks becomes a prominent need, especially in safety critical situations such as AI for healthcare, manufacturing and policy making. This series of talks introduces Bayesian deep learning, a paradigm that introduces Bayesian modelling ideas to the world of deep learning, with benefits of uncertainty quantification and enabling optimal sequential decision making. The crash course will start from mathematical introductions on Bayesian linear regression, Gaussian processes and the concept of Bayesian neural networks. Then the mainstream algorithms and applications of Bayesian neural networks will be discussed. Lastly, based on the introduced materials including uncertainty decomposition techniques, a modern application of the Bayesian deep learning framework to Large Language Model (LLM) in-context learning will be showcased.

报告时间：2025年7月16日  09:00-11：30

报告地点：二校区西配楼BX11

报告人简介：Yingzhen Li is an Associate Professor  in Machine Learning at the Department of Computing, Imperial College London, UK. Before that she was a senior researcher at Microsoft Research Cambridge, and previously she has interned at Disney Research. She received her PhD in engineering from the University of Cambridge, UK. Yingzhen is passionate about building reliable machine learning systems, and her approach combines both Bayesian statistics and deep learning. She has worked extensively on approximate inference methods with applications to Bayesian deep learning and deep generative models, and her work has been applied in industrial systems and implemented in deep learning frameworks (e.g. Tensorflow Probability and Pyro). She regularly gives tutorials and lectures on probabilistic ML and generative models at machine learning research summer schools, as well as invited tutorials on Advances in Approximate Inference at NeurIPS 2020 and UAI 2025. She was a co-organiser of the Advances in Approximate Bayesian Inference (AABI) symposium in 2020-2023, as well as many NeurIPS/ICML/ICLR workshops on topics related to probabilistic learning. She is a Program Chair for AISTATS 2024 and a General Chair for AISTATS 2025 and 2026. Her work on Bayesian ML has also been recognised in AAAI 2023 New Faculty Highlights.。