YICHUN HU 

2 W Loop Rd, New York, NY 10044 
(+1)607-262-2847 yh767@cornell.edu 

EDUCATION 

Cornell University 
Ph.D. Candidate in Operations Research, minor in Applied Mathematics 
Advisor: Nathan Kallus 
08/2017 -05/2022 
Peking University 
B.S. in Mathematics and Applied Mathematics, B.A. in Economics 
09/2013 -06/2017 
RESEARCH INTERESTS 

Data-driven decision making; bandit/RL; sequential decision making; causal inference; operation research. 

RESEARCH PAPERS 

Publications 

1. Y. Hu, N. Kallus, X. Mao. Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable 
Regret Regimes. Operations Research, accepted 2021. 

• Preliminary version appeared in 33rd Conference on Learning Theory (COLT 2020). 
• Finalist, INFORMS Applied Probability Society 2020 Best Student Paper Competition. 


2. Y. Hu, N. Kallus, M. Uehara. Fast Rates for the Regret of Offline Reinforcement Learning. 34th Conference 
on Learning Theory (COLT 2021). 

• Journal version under review at Mathematics of Operations Research. 

Under Review/Revision 

1. Y. Hu, N. Kallus, X. Mao. Fast Rates for Contextual Linear Optimization. Revised and Resubmitted to 
Management Science, 2020. 
2. Y. Hu, N. Kallus. DTR Bandit: Learning to Make Response-Adaptive Decisions with Low Regret. Under 
review at Journal of the American Statistical Association, 2020. 
3. M. Garrard, H. Wang, B. Letham, S. Singh, A. Kazerouni, S. Tan, Z. Wang, M. Huang, Y. Hu, C. Zhou, N. 
Zhou, E. Bakshy. Practical Policy Optimization with Personalized Experimentation. Submitted, 2021. 


WORK EXPERIENCE 

Facebook Menlo Park, CA (Remote) 
Research Engineer Intern, Core Data Science (Adaptive Experimentation) 05/2021-08/2021 

• Researched on multi-objective contextual bandit learning and value model tuning in personalized experiments. 

Google Mountain View, CA (Remote) 
Data Scientist Intern, Google Play 05/2020-08/2020 

• Researched on causal methods to analyze the impact of app usage on the retention rate of Google Play Pass. 

SELECTED HONORS 

Finalist, Applied Probability Society Best Student Paper Competition, INFORMS 2020 
Sherri Koenig Stuewer Graduate Fellowship, Cornell University 2018 
Excellent Graduate Award, Peking University 2017 
Award for Academic Excellents, Peking University 2015,2016 
May Fourth Scholarship, Peking University 2016 
Kwuang-Hua Scholarship, Peking University 2015 
SKILLS 

Programming: Python (PyTorch), R, Julia. 


PRESENTATIONS 

RL Theory Seminar, Virtual 11/2021 (Scheduled) 
INFORMS Annual Meeting, Anaheim, CA 10/2021 
16th INFORMS Workshop on Data Mining and Decision Analytics, Anaheim, CA 10/2021 
34th Annual Conference on Learning Theory (COLT 2021), Boulder, CO 08/2021 
INFORMS Annual Meeting, Virtual 11/2020 
15th INFORMS Workshop on Data Mining and Decision Analytics, Virtual 11/2020 
33rd Annual Conference on Learning Theory (COLT 2020), Virtual 07/2020 
INFORMS Annual Meeting, Seattle, WA 10/2019 
14th INFORMS Workshop on Data Mining and Decision Analytics, Seattle, WA 10/2019 
Cornell ORIE Young Researchers Workshop, Ithaca, NY 10/2019 
TEACHING EXPERIENCE 
Cornell University, Teaching Assistant 
• CS 5785: Applied Machine Learning Fall 2019 
• ORIE 4360: A Mathematical Examination of Fair Representation Fall 2018 
• ORIE 3510: Introduction to Engineering Stochastic Processes I Spring 2018 
• ORIE 5600: Financial Engineering with Stochastic Calculus I Fall 2017 
SERVICE 

• Journal Reviewer: Operations Research 
• Conference Reviewer: ICML 2020-2021, ICLR 2021, AISTATS 2021-2022, NeurIPS 2021 
• Workshop Reviewer: NeurIPS 2021 Workshop on Causal Inference Challenges in Sequential Decision Making 
• Session chair: INFORMS 2020 General Session (Stochastic Bandits) 
• Cornell University ORGA (Operations Research Graduate Association) Tech Liaison 2019-2020