Jiuyao Lu

Email: jiuyaolu at wharton dot upenn dot edu

Hello! I'm a second-year PhD student in the Department of Statistics and Data Science at the Wharton School of the University of Pennsylvania, working with Professors Michael Kearns, Aaron Roth, and Zhimei Ren.

This summer, I am an Applied Scientist Intern at Amazon, working on post-training for reasoning models and calibrated prediction for decision making.

I received my B.S. in Mathematics from Tsinghua University and my M.S. in Biostatistics from Johns Hopkins University.

My first name is pronounced Joe-Yow, and I also go by Joe.

Selected Recent Papers [google scholar]

• MatrAIx: Simulating the World with 8.3 Billion Persona Agents
  Xiaomin Li et al.
  Preprint
• Sample Complexity of Multicalibration for Multilevel Properties
  Jiuyao Lu, Krishnakumar Balasubramanian, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan
  Preprint
• Optimal Lower Bounds for Online Multicalibration
  Natalie Collina, Jiuyao Lu, Georgy Noarov, Aaron Roth (alphabetical order)
  FOCS 2026
  
• Stronger Benchmarks for Prediction as a Service with Constraints
  Yahav Bechavod, Jiuyao Lu, Aaron Roth (alphabetical order)
  ICML 2026
• Omniprediction with Long-Term Constraints
  Yahav Bechavod, Jiuyao Lu, Aaron Roth (alphabetical order)
  COLT 2026

Teaching

I have served as a teaching assistant for the following courses at the University of Pennsylvania:

• Probability (2025)
• Introductory Business Statistics (2025)

and at Johns Hopkins University:

• Advanced Data Science I–II (2023)
• Statistical Theory I–IV (2022–2023)

Academic Service

Reviewer: ICML 2026 (Silver Reviewer), NeurIPS 2026, FOCS 2026