I obtained my PhD degree at Department of Computer Science, University of Toronto, supervised by Roger Grosse. Previously, I did my undergraduate at Department of Electronic Engineering, Tsinghua University.
My research focuses on machine learning, especially the combination between Bayesian methods and deep neural networks. I aim to leverage probabilistic methods to improve the quality, reliability and efficiency of machine learning systems. Specifically, I investigate how to provide uncertainty estimation in probabilistic models and exploit the uncertainty to improve the robustness and guide exploration. Furthermore, I am interested in improving the learning efficiency and out-of-distribution generalization of intelligent systems, such as in continual learning and meta-learning.
CV / Github / Google Scholar / Twitter
Research
Peer-Reviewed Papers
- Information-theoretic Online Memory Selection for Continual Learning ICLR. 2022
- Understanding the Variance Collapse of SVGD in High Dimensions ICLR. 2022
- Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition ICML. 2021
- Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?[oral] AISTATS. 2021
- Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes NeurIPS. 2019
- Functional Variational Bayesian Neural Networks ICLR. 2019
- Aggregated Momentum: Stability Through Passive Damping ICLR. 2019
- Differentiable Compositional Kernel Learning for Gaussian Processes ICML. 2018
- Noisy Natural Gradient as Variational Inference ICML. 2018
- A Spectral Approach to Gradient Estimation for Implicit Distributions ICML. 2018
- Kernel implicit variational inference ICLR. 2018
- Learning structured weight uncertainty in bayesian neural networks AISTATS. 2017
- On the Spectral Efficiency of Massive MIMO Systems With Low-Resolution ADCs. IEEE Communications Letters. 2016