About

Hi, I am a fifth year PhD student in Econometrics and Statistics at the University of Chicago Booth School of Business, supervised by Bryon Aragam. Before joining Booth, I earned my MS in Statistics at UChicago, advised by Jingshu Wang and worked with Dacheng Xiu. Prior to that, I obtained my BS in Statistics from Renmin University of China and was working with Xiaoling Lu and Danhui Yi. I grew up in Fuzhou, Fujian.


I am on the 2025-2026 academic job market!
My CV is here.

Me generated by Nano Banana

Research

KL-BSS: Rethinking optimality for neighbourhood selection in structural equation models
M Gao, WM Tai and B Aragam
Reject & Resubmit invited at JRSS-B, 2025
preprint / software

Optimal structure learning and conditional independence testing
M Gao, Y Wang and B Aragam
Submitted, 2025
preprint

Optimality and computational barriers in variable selection under dependence
M Gao and B Aragam
Submitted, 2025
preprint

Optimizing return forecasts: A Bayesian intermediary asset pricing approach
M Gao and C Zhang
Submitted, 2024 (Presented at SFS Cavalcade North America 2025)
preprint

Joint Trajectory Inference for Single-cell Genomics Using Deep Learning with a Mixture Prior
J Du, T Chen, M Gao and J Wang
PNAS, 2024
journal / preprint / software

Optimal estimation of Gaussian (poly)trees
Y Wang, M Gao, WM Tai, B Aragam and A Bhattacharyya
AISTATS, 2024
proceedings / preprint / software

Multivariate change point detection for heterogeneous series
Y Guo, M Gao and X Lu
Neurocomputing, 2022
journal

Optimal estimation of Gaussian DAG models
M Gao, WM Tai and B Aragam
AISTATS, 2022
proceedings / preprint

Efficient Bayesian network structure learning via local Markov boundary search
M Gao and B Aragam
NeurIPS, 2021
proceedings / preprint / software

Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families
G Rajendran, B Kivva, M Gao and B Aragam
NeurIPS, 2021
proceedings / preprint

A polynomial-time algorithm for learning nonparametric causal graphs
M Gao, Y Ding and B Aragam
NeurIPS, 2020
proceedings / preprint / software

Professional Service

  • Referee

    JMLR, JCGS, CSDA, TMLR, Reviewer
    NeurIPS, 2022-2025, Reviewer
    AISTATS, 2022-2026, Reviewer
    ICML, 2023-2025, Reviewer
    ICLR, 2025-2026, Reviewer
    CLeaR, 2025, Reviewer
    UAI, 2025, Reviewer
    AAAI, 2025, Reviewer

  • Teaching

    Business Statistics, 2024-2026, TA
    Probability and Statistics, 2023-2024, TA
    Bayes, AI and Deep Learning, 2025, TA