Mohammad Mehrabi

I am a postdoctoral scholar in Operations, Information & Technology at Stanford Graduate School of Business, where I am fortunate to be advised by Stefan Wager and Ömer Karaduman.  Prior to Stanford,  I received my Ph.D. in August 2023 from the Department of Data Sciences and Operations at USC Marshall School of Business, where I had the privilege of being supervised by Adel Javanmard. 

My research is broadly at the intersection of machine learning, statistics, and optimization for data-driven decision-making. Methodologically, I am interested in the design and analysis of reliable and robust statistical methods. In an applied context, I am interested in developing models and algorithms within the scope of market design and dynamic pricing with applications for demand response programs in residential electricity markets.

Projects Under Revision 

•  Optimal Mechanisms for Demand Response: An Indifference Set Approach 

  with Omer Karaduman, and Stefan Wager,  Submitted to Management Science, 2025

• Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap 

          with Stefan Wager, Submitted to Operations Research, 2024

Journal Publications  

•   Pearson Chi-squared Conditional Randomization Test

  with Adel Javanmard, accepted for publication at IEEE Transactions on Information Theory, 2025.

•  Adversarial Robustness for Latent Models: Revisiting the Robust-Standard Accuracies Tradeoff

  with Adel Javanmard, Operations Research 72, no. 3,  2024.

• GRASP: a Goodness-of-fit Test for Classification Learning

  with Adel Javanmard, Journal of the Royal Statistical Society Series B: Statistical Methodology 86.1 (2024): 215-245.

• Online Debiasing for Adaptively Collected High-Dimensional Data with Applications to Time Series Analysis

  with Yash Deshpande, Adel Javanmard, Journal of the American Statistical Association 118, no. 542, 2023.

• Error-correction for Sparse Support Recovery Algorithms

  with Aslan Tchamkerten, IEEE Transactions on Information Theory 68.11 (2022): 7396-7409.

Conference Publications 

• Optimal Mechanisms for Demand Response: An Indifference Set Approach 

  with Omer Karaduman, and Stefan Wager,  ACM Conference on Economics and Computation (EC), 2025.

• Fundamental Tradeoffs in Distributionally Adversarial Training

  with Adel Javanmard, Ryan A. Rossi, Anup Rao, and Tung Mai, International Conference on Machine Learning, 2021.

• A Model-free Closeness-of-influence Test for Features in Supervised Learning

        with Ryan A. Rossi,  International Conference on Machine Learning, 2023.

• Error-correction for Sparse Support Recovery Algorithms

  with Aslan Tchamkerten, IEEE International Symposium on Information Theory (ISIT), 2021.

• Bounds on Approximation Power of Feedforward Neural Networks

        with Aslan Tchamkerten, and Mansoor Yousefi, International Conference on Machine Learning, 2018.

Selected Talks

Optimal Mechanisms for Demand Response: An Indifference Set Approach

• INFORMS Revenue Management and Pricing Conference, Columbia Business School, July 2025

• ACM Conference on Economics and Computation (EC), Stanford University, July 2025 

• INFORMS Applied Probability Society Conference, Georgia Institute of Technology, June 2025

• Commodity and Energy Markets Annual Meeting, Jones Graduate School of Business, Rice University, June 2025 

• Marketplace Innovation Workshop, Virtual, May 2025

• SoCal OR/OM Day, Paul Merage School of Business at UC Irvine,  May 2025

• Data-Driven Research Seminar,  Stanford University, Nov 2024

• INFORMS Annual Meeting, Seattle WA, Oct 2024

• Causal Science Center Conference (SC²), Stanford University, Oct 2024

Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap 

• Causal Science Center Conference on Experimentation (poster), Stanford University, May 2024

• Stanford Data Science Conference (poster), Stanford University, May 2024

• Econometrics Student Workshop, Stanford University, Feb 2024