Wei Tang

About Me

I am a postdoctoral fellow at the Data Science Institute, Columbia University, mentored by Shipra Agrawal. I completed my Ph.D. in Computer Science at Washington University in St. Louis, where I was fortunate to be advised by Chien-Ju Ho. I received my bachelor degree from Tianjin University, China.

The goal of my research is to develop theoretically rigorous and empirically grounded algorithms for decision-making schemes in dynamic, uncertain, and human-centric online marketplaces. Towards this goal, I pursue three complementary research themes using ideas from machine learning (e.g., online learning), algorithmic economics, and behavioral (social) sciences:

  1. designing new learning algorithms to balance the exploration and exploitation tradeoff in uncertain dynamic environments, especially when additional problem structures, e.g., information asymmetries, are present;
  2. designing behavior-aware algorithms taking into account different human behaviors;
  3. designing socially-aware algorithms considering societal impact when deploying the designed algorithms in modern marketplaces.

I am on the 2023-2024 job market. My [CV]. Email: wt2359 at columbia dot edu

Upcoming Talks:
  1. Oct 06 Harvard EconCS Seminar
  2. INFORMS Annul Meeting -- Session TC67 (Applied Online Learning and Decision-making)
    Tue, Oct 17, 2023, 12:45 PM - 2:00 PM; CC-West 104A; Talk 2
    Dynamic Pricing and Learning with Bayesian Persuasion

Working Paper

  • Dynamic Pricing and Demand Learning with Averaging Reference Effect
    (α-β). Shipra Agrawal, Wei Tang.
    Under preparation

  • Rationality-Robust Information Design: Bayesian Persuasion under Quantal Response
    (α-β). Yiding Feng, Chien-Ju Ho, Wei Tang.
    Accepted for presentation at the 34th Stony Brook International Conference on Game Theory, July 2023
    [full version] [arxiv]



It's also been my good fortune to be working with: Bolin Ding, Yiding Feng, Yang Liu, Saumik Narayanan, Haifeng Xu, Ming Yin, Guanghui Yu.