Yu-Xiang Wang's Homepage
|
Yu-Xiang Wang 王宇翔Eugene Aas Chair Assistant Professor Department of Computer Science, Co-Director, Center for Responsible Machine Learning UC Santa Barbara Office: HFH-2121 E-mail: yuxiangw AT cs.ucsb.edu Yu-Xiang is pronounced approximately as ['ju:'ʃi:ʌŋ], namely, y~eu~ee - sh~ih~ah~ng . Looking for self-motivated students and postdocs. |
Welcome
Hello! Welcome to my homepage. I am a faculty member of the computer science department in UCSB. Prior joining UCSB, I was a scientist with Amazon AI in Palo Alto. Even before that I was with the Machine Learning Department in Carnegie Mellon University and had the pleasure of being jointly advised by Stephen Fienberg, Alex Smola, Ryan Tibshirani and Jing Lei.
Over the years I have worked on a diverse set of problems in the broad area of statistical machine learning, e.g., trend filtering, differential privacy, subspace clustering, large-scale learning / optimization, bandits / reinforcement learning, just to name a few. Check out my publication page for details. My most recent quests include making differential privacy practical and developing a statistical foundation for off-policy reinforcement learning.
Teaching
- (New course!) CS292F Reinforcement Learning (2021 Spring): [course website]
- CS165A Artificial Intelligence (2020 Fall): [course website]
- CS292F Convex Optimization (2020 Spring): [course website]
- CS165A Artificial Intelligence (2020 Winter): [course website]
- CS292A Convex Optimization (2019 Spring): [course website]
- CS165A Artificial Intelligence (2019 Winter): [course website]
Publications, Google Scholar profile
News
- Mar 2021: Excited to receive two awards from Google: PhD Fellowship for Yuqing Zhu and a Research Scholar Award for me. Thanks Google for the generous support!
- Mar 2021: Excited to receive NSF CAREER Award that supports our research in differential privacy.
- Mar 2021: autodp v0.2 is released with a brand new "mechanism" api and support for f-DP and privacy profiles on top of RDP.
- Feb 2021: A few manuscripts released: topics on Optimal Offline RL, dynamic regret in nonstochastic control, logarithmic regret in dynamic pricing, and differentially private federated learning.
- Jan 2021: Three papers accepted to AISTATS on optimal offline RL via uniform convergence, online forecasting with Aligator (parameter-free adaptive minimax and practical!) and a theory of differentially private PATE learning. Congratulations to S2ML team: Dheeraj (check out his new homepage), Xuandong, Chong, Yuqing, Ming; and our awesome colleagues Yu Bai at Salesforce research and Kamalika at UC San Diego.
- Dec 2020: Paper Inter-Series Attention Model for COVID-19 Forecasting" is accepted to SDM 2021. Congratulations Xiaoyong and Prof. Xifeng Yan.
- Dec 2020: Co-organized NeurIPS Workshop on Privacy Preserving Machine Learning.
- Dec 2020: Spoke at the Berkeley Simons Institute Workshop on Reinforcement Learning from Batch Data and Simultation. Thanks the organizers for putting together the excellent week-long program!
- Oct 2020: The second annual CRML Summit on "AI and COVID'19" comes with a very exciting program with 3 keynotes, 11 invited talks and a panel discussion! All are welcome! See here for detailed program.
- Oct 2020: Spoke at the RL Theory virtual seminar on uniform convergence in OPE [Slides here].
- Sep 2020: Three papers accepted to NeurIPS 2020. Topics include differential Privacy, domain adaptation, online trend forecasting (see here) . Congratulations to my students Dheeraj and Yuqing! Also, congratulations to Remi from Microsoft Research and Han who is starting in CS@UIUC as an assistant professor.!
- Aug 2020: Happy to receive NSF Award that funds our research on Offline Reinforcement Learning.
- June 2020: Paper on "Differentially Private Topic Model (Latent Dirichlet Allocation)" accepted to ICML 2020. Congrats, Prof. Furong Huang and her excellent undergraduate researcher Chris DeCarolis!
- July 2020: We appreciate the generous gifts from: Google and Evidation Health.
- May 2020: Happy to receive NSF-Intel Award that funds our collaboration (with Arpit and Elizabeth) on RL approaches for self-driving networks!
- Mar 2020: Happy to receive NSF RAPID Award that funds on our research (with Xifeng) on forecasting models for COVID'19. See a website here.
- Feb 2020: Paper "Private-kNN: Practical Differential Privacy for Computer Vision" accepted to CVPR 2020. Congrats, Yuqing!.
- Jan 2020: Paper "Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning" accepted to AISTATS 2020. Congrats, Ming Yin!
- Dec 2019: We appreciate the generous gifts from: Amazon, Adobe, NEC Labs, Appfolio.
- Oct 2019: Visiting UC San Diego, spoke on Online Nonparametric Forecasting here.
- Sep 2019: Four papers accepted to NeurIPS 2019. Topics include Reinforcement Learning, Time Series Forecasting and Online Learning (see here) . Congrats, Dheeraj, Shiyang, Yu Bai , Tengyang!
- June 2019: Spoke in an invited session at the ICML EXPO workshop on "Machine Learning for All-Inclusive Finance" on privacy and fairness. Slides can be found here.
- June 2019: My students Dheeraj Baby and Chong Liu shared our recent work on "Online Forecasting" and Doubly Robust Crowdsourcing" at Time Series workshop and the Human In the Loop Learning (HILL) Workshop at ICML'18.
- Apr 2019: Paper "Poisson Subsampled Renyi Differential Privacy" is accepted to ICML'19. Congrats, Yuqing!
- Apr 2019: Our paper "Subsampled Renyi Differential Privacy and Analytical Moments Accountant" with Borja Balle and Shiva Kasiviswanathan received the Notable Paper Award from AISTATS'2019. Thanks anonymous reviewers and AISTATS organizers!
- Apr 2019: Spoke at the Simons Institute Workshop on Privacy and the Science of Data Analysis (see the slides here).