I am an Assistant Professor in UMass Amherst's Manning College of Information and Computer Sciences, working on learning theory and theoretical computer science in general.
Previously, I was a FODSI postdoc at UC Berkeley and MIT hosted by Nika Haghtalab and Ronitt Rubinfeld. I received my PhD in Computer Science from Stanford University, where I was advised by Gregory Valiant. Prior to that, I received my B.Eng. in Computer Science from Yao Class at Tsinghua University.
If you are interested in working with me at UMass, apply to our PhD program (see here for details) and mention my name in your application. Also feel free to reach out via email if you are interested in my research.
Research Interests
My research interests lie in learning theory and theoretical computer science in general. Below is a clustering of part of my recent work:
Theoretical aspects of prediction, learning, and decision-making in online settings: [QV STOC'21, QV COLT'21, QV ITCS'23, QZ COLT'24, HQYZ NeurIPS'24, QZ COLT'25]
Theoretical foundations of collaborative and federated learning, from both learning- and game-theoretic perspectives: [DQ ICML'24, HQY SODA'25]
New and simple approaches to dealing with adversarial corruption and heterogeneity in statistical inference: [QGRDZ NeurIPS'22, KQS ITCS'24]
Selected Recent Papers (Full List)
Truthfulness of Decision-Theoretic Calibration Measures. COLT 2025 (forthcoming)
Mingda Qiao, Eric Zhao
On the Distance from Calibration in Sequential Prediction. COLT 2024
Mingda Qiao, Letian Zheng
Properly Learning Decision Trees in Almost Polynomial Time. FOCS 2021
Guy Blanc, Jane Lange, Mingda Qiao, Li-Yang Tan
[arXiv][conference version][journal version][video][Guy's TCS+ talk]
Invited to FOCS 2021 special issue
Journal of the ACM, 2022
Stronger Calibration Lower Bounds via Sidestepping. STOC 2021
Mingda Qiao, Gregory Valiant
[arXiv][conference version][video]
Professional Services
Program Committee: COLT 2025 (Senior PC)
Conference Reviewer: STOC (2020, 2024), FOCS (2021, 2025), SODA (2024, 2025), ITCS (2024, 2025), ICML (2019, 2023--2025), NeurIPS (2019, 2021--2025), AISTATS (2019--2022, 2024, 2025)
Journal Reviewer: SIAM Journal on Computing, Journal of Machine Learning Research, IEEE Transactions on Information Theory