Qiang Liu
 |
Qiang Liu ("Qiang" sounds like "Chee-ah-ng", and "Liu" as "l-yo") |
Research
My research area is machine learning and statistics, with interests spreading over the pipeline of data collection (e.g., by crowdsourcing), learning, inference, decision making, and various applications using probabilistic modeling.
Examples of topics of interest: /probabilistic graphical models; variational and Monte Carlo inference; deep learning; neural architecture optimization; energy-efficient learning; deep reinforcement learning; distributed learning; big data problems; kernel and nonparametric methods, etc.
I am an action editor of Journal of Machine Learning Research (JMLR).
Selected / Recent Publications and Slides
New. Steepest Descent Architecture Optimization: Going Beyond Black Boxes [ paper, paper, slides, poster ]
New. Probabilistic Learning and Inference Using Stein's Method [Project Page, slides v1, slides v2]
- Stein Variational Gradient Descent
NeurIPS2016, NeurIPS2017, NeurIPS2018, [code] [more]
- Distributed Estimation, Information Loss and Exponential Families
Liu, Ihler; Advances in Neural Information Processing Systems (NIPS) 2014.
- Reasoning and Decisions in Probabilistic Graphical Models - A Unified Framework
Liu; PhD Thesis, Fall 2014
- Variational Algorithms for Marginal MAP
Liu, Ihler; Journal of Machine Learning Research (JMLR) 2013.
- Variational Inference for Crowdsourcing
Liu, Peng, Ihler; Advances in Neural Information Processing Systems (NIPS) 2012. [Appendix, Code]
