Hi there! My name is Yingzhen (映真) and I hope you enjoy this website. 😀
I'm interested in building reliable machine learning systems which can generalise to unseen environments. I approach this goal using probabilistic modelling and representation learning, some of my research topics include:
- (deep) probabilistic graphical model design;
- fast and accurate (Bayesian) inference/computation techniques;
- uncertainty quantification for computation and downstream tasks;
- robust and adaptive machine learning systems.
In general I'm also interested in transfer/meta learning, information theory, optimisation, and sequential data modelling.
I am currently an Associate Professor in Machine Learning at the Department of Computing at Imperial College London. See the info for prospective students or info for collaborating with me. Since Mar 2024 I am also a Turing Fellow at The Alan Turing Institute. Before coming back to academia, I've spent 2.5 wonderful years as a senior researcher at Microsoft Research Cambridge.
I read my PhD with Prof. Richard E. Turner in machine learning at the University of Cambridge, where I was also a member of Darwin College. My PhD thesis is about approximate inference. If you want to know more about approximate inference & probabilistic ML, check out the following materials:
- NeurIPS 2020 tutorial on "Advances in Approximate Inference" (with Cheng Zhang)
- ProbAI 2022 tutorial on "Introduction to Bayesian Neural Networks"
- GeMSS 2023 tutorial on "Sequential Generative Models"
- AAAI 2023 new faculty highlight "Robust and Adaptive Deep Learning via Bayesian Principles" [talk video]
- An incomplete list of topics in approximate inference (still updating)