I am interested in topics in economics and machine learning, seeking to design and investigate the effects of efficient, incentive-aware systems and policies in microeconomic contexts using theoretical and empirical frameworks.
- Reinforcement learning and bandits
- (Algorithmic) game theory/mechanism design
- Econometrics (causal inference, policy learning)
- Labor and applied microeconomics
Working Papers
EconCS
[7] SPADE: Stochastic Payoff-Based Algorithm for Decentralized Equilibria in Games with Decision-Dependent Distributions and Coupled Constraints, 2026
- Kenny Guo, William Chang, Xuanyu Cao
[6] Youdunit: Single-Call Counterfactual Necessity in Multi-Agent LLM Systems, 2026
- Marissa Zhao Li, Stephanie Gao, Kenny Guo, Xingjian Li, William Chang, Goran Radanovic
- Kenny Guo, Ricardo Parada, Helen Yuan, Larissa Xu, William Chang
[4] Coordinating for Clicks: Learning in Multi-Agent Information Asymmetric Cascading Bandits, 2025
- Kenny Guo, Lily Jiang, Lune Chan, Sophia Yi, William Chang
AI/ML
[3] Learning Adversarial Continuous MDPs with Bandit Feedback and Unknown Transitions, 2026
- Aarush Kulkarni, Khang Nguyen, Ricardo Parada, Kenny Guo, William Chang, Yan Dai
[2] Policy Optimization for Corrupted Markov Decision Processes, 2025
- Khang Nguyen, Kenny Guo, William Chang
Public/Labor Economics
[1] Inflation on UI Program Benefits and Affordability for the Unemployed, 2026
- Kenny Guo*, Terrence Yu*, Peter Mannino
- Previously titled “Impacts and Policy Implications of Inflation and Declining Real UI Benefit Levels”
Publications/Accepted Papers
AI/ML
[1] Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs
- Kenny Guo, Valentio Iverson, Sahan Wijetunga, William Chang
- Accepted to Conference on Uncertainty in Artificial Intelligence (UAI 2026)
Presentations/Conferences
Upcoming
- 42nd Conference on Uncertainty in Artificial Intelligence (UAI 2026), Amsterdam, Netherlands, August 17-21, 2026
Past
- Undergraduate Research Week (5/19/2025-5/23/2025)
- Variations on Information Asymmetric Multi-Agent Reinforcement Learning Bandit Problems, with Lily Jiang and Khang Nguyen [Video]
- Impacts and Policy Implications of Inflation and Declining Real UI Benefit Levels, with Terrence Yu
- Economic Board of Visitors Meeting (4/28/2025)
- UI and Inflation
- SoCal AI and Responsibility Summit (SAIRS) (4/19/2025)
- Coordinating for Clicks: Learning in Multi-Agent Information Asymmetric Cascading Bandits, with Helen Yuan
- Winner of Best Overall Contribution to 2025 Research Competition