Mirah Shi

Hello! I'm a fourth-year PhD student in computer science at the University of Pennsylvania, where I'm fortunate to be advised by Michael Kearns and Aaron Roth. I work at the intersection of machine learning theory, economics, and society. I am particularly interested in understanding how incentives, information, and learning shape interactions between ML/AI systems and human decision-makers. To this end, I have worked on theoretical frameworks for multi-agent systems that promote trustworthiness, collaboration, and alignment.

I am grateful to be supported by a Google PhD Fellowship. My research has also been supported by AWS AI. Before coming to Penn, I received my bachelors in math from Barnard College. I pronounce my name my-ra shee.

Email: mirahshi at seas.upenn.edu

Recent News

• Fall 2025: Honored to be awarded the Google PhD Fellowship!
• Summer 2025: Spending the summer at Morgan Stanley on the ML Research Team.
• Summer 2025: Co-organizing the EC Gender Inclusion Workshop!

Publications [google scholar]

• Emergent Alignment via Competition
  Natalie Collina, Surbhi Goel, Aaron Roth, Emily Ryu, Mirah Shi
  Preprint


• Learning to Acquire Resources in Competition
  Safwan Hossain*, Mirah Shi*, Andrew Bennett, Neil Chriss, Michael Kearns, Anderson Schneider, Yuriy Nevmyvaka
  Preprint


• Algorithmic Aspects of Strategic Trading
  Michael Kearns, Mirah Shi
  Preprint


• Collaborative Prediction: Tractable Information Aggregation via Agreement
  Natalie Collina, Ira Globus-Harris, Surbhi Goel, Varun Gupta, Aaron Roth, Mirah Shi
  SODA 2026
  Presented at EC 2025 Workshop on Human-AI Collaboration (spotlight)
  Presented at TTIC Workshop on Incentives for Collaborative Learning and Data Sharing (spotlight)


• Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Losses
  Jiuyao Lu, Aaron Roth, Mirah Shi
  COLT 2025
  


• An Elementary Predictor Obtaining \(2\sqrt{T}+1\) Distance to Calibration
  Eshwar Ram Arunachaleswaran, Natalie Collina, Aaron Roth, Mirah Shi
  SODA 2025
  NeurIPS 2024 ML-OPT Workshop


• Forecasting for Swap Regret for All Downstream Agents
  Aaron Roth, Mirah Shi
  EC 2024
  Presented at ESIF Economics & AI+ML Meeting 2024


• Filtering Higher-Order Datasets
  Nicholas Landry, Ilya Amburg, Mirah Shi, Sinan Aksoy
  Journal of Physics: Complexity (2024)
  


• Center-Embedding and Constituency in the Brain and a New Characterization of Context-Free Languages
  Daniel Mitropolsky, Adiba Ejaz, Mirah Shi, Christos Papadimitriou, Mihalis Yannakakis
  Natural Logic Meets Machine Learning Workshop 2022
  

Teaching

I've been a teaching assistant for the following courses at Penn:

• NETS 4120 Algorithmic Game Theory (Spring 2024)
• CIS 6250 Theory of Machine Learning (Fall 2022)

• COMS 3261 Computer Science Theory (Spring 2021)

Other

• I help organize the Theory Seminar at Penn. Feel free to reach out if you'd like to give a talk!
• I spent the summer of 2021 doing research at Pacific Northwest National Laboratory, hosted by Sinan Aksoy.