Mentored Research

I’m the founder of BruinML. I founded this group in January of 2024. Currently the president is Kenny Guo

I have had the privilege of mentoring many amazing students in research projects since Spring 2024. Below are some of my most common areas (and I’m looking to expand this by a lot). If you’re interested in a project please let me know chang314@g.ucla.edu.

Multiplayer Bandits
We study the information asymmetry mutliplayer bandits applied to various bandit problems. One of my top students wrote a blog on this after he submitted the Cascading paper. See here for more details.

1. DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits For Multiple Clicks
   Andy Wang, Charlton Shih, William Chang
   Under Review at Association for the Advancement of Artificial Intelligence, 2025

2. Adversarially Robust Latent Bandits in Multiplayer Asymmetric Settings
   Helen Yuan, Kanzah Areej Jamil, Vanessa Jolie Pare, William Chang
   Under Review at Neural Information Processing Systems, 2025

3. Multiplayer Information Asymmetric Linear Combinatorial Bandits
   Jacqueline Liu, Bree Chen, Xingjian Li, Yuxi Luo, William Chang
   Under Review at Neural Information Processing Systems, 2025

4. The Learnability of the Multiplayer Adversarial Bandit Problem
   David Yu, Khang Nguyen, Daniel Yu, William Chang
   Under review at Conference in Decision and Control 2025

5. Improved Multiplayer Bandit Algorithms for Bernoulli Noise
   Brook Chuang, William Chang
   Under review at Conference in Decision and Control 2025

6. Heavy Tailed Reward Distributions for Multiplayer Bandits
   Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang
   Under review at Conference in Decision and Control 2025

7. Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits,
   Ricardo Parada, Chenzhang Zhao, William Chang
   Under review at Conference in Decision and Control 2025

8. Multiplayer Information Asymmetric Bandits in Metric Spaces [PDF]
   William Chang, Aditi Karthik
   Under review at Transactions of Machine Learning Research

9. Multi-Player Information Asymmetric Multiple Arm Identification [PDF]
   Larissa Xu, Jasmine Nguyen, William Chang
   Under review at Journal of Machine Learning Research

10. Coordinating for Clicks: Learning in Multi-Agent Information Asymmetric Cascading Bandits [PDF]
    Kenny Guo, Lily Jiang, Lune Chan, Sophia Yi, William Chang
    Under review at Journal of Machine Learning Research

11. Multiplayer Information Asymmetric Contextual Bandits [PDF]
    William Chang, Terry Lu
    Transactions of Machine Learning Research 2025

12. Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication [PDF]
    William Chang, Terry Lu
    IEEE Conference on Decision and Control, 2024

Bandits

1. Tight Regret Bounds in Multi-Armed Bandits with Heterogeneous Variances
   Lynn Tanisaka, Helen Yuan, Solomon Xu, Brandon Chang, Sophia Yi, William Chang
   Under Review at Association for the Advancement of Artificial Intelligence, 2025

2. Best Arm Identification in Lipschitz Bandits: Uniform and Adaptive Strategies
   Khang Nguyen, Larissa Xu, Lily Jiang, William Chang
   Under Review at Association for the Advancement of Artificial Intelligence, 2025

Markov Decision Processes

1. Coordinating the Best Policy in Information Asymmetric MDPs
   Helen Yuan, Kanzah Areej Jamil, Chenzhang Zhao, Xingjian Li, William Chang
   Under Review at Association for the Advancement of Artificial Intelligence, 2025

2. Policy Optimization for Corrupted Markov Decision Processes
   Khang Nguyen, Kenny Guo, David Yu, William Chang
   Under Review at Neural Information Processing Systems, 2025

3. Cooperative Information Asymmetric Multiplayer Learning in Markov Decision Processes
   Larissa Xu, King Bi, William Chang
   Under Review at Neural Information Processing Systems, 2025