Amine Bennouna

Kellogg School of Management
Northwestern University

Contact: amine.bennouna [at] kellogg.northwestern [dot] edu
CV, Google Scholar, LinkedIn


Hello! I am an Assistant Professor in Operations at the Kellogg School of Management, Northwestern University. Prior to that, I spent one year as a postdoctoral researcher at the MIT Laboratory for Information & Decision Systems (LIDS), working with Prof. Asuman Ozdaglar and Prof. Saurabh Amin.

I completed my PhD at the MIT Operations Research Center in 2024, advised by Prof. Bart Van Parys. Prior to joining MIT, I graduated from Ecole Polytechnique in 2019 majoring in Applied Mathematics.


headshot

My research focuses on understanding how machines, or artificial intelligence (AI), learn to make decisions. Specifically, I work on developing novel learning algorithms to enable efficient, data-driven decision-making while emphasizing key reliability attributes. Enhancing these learning algorithms has significant practical implications, driven by the rapid adoption of AI, and is based on fascinating mathematical models. My research involves theoretical and algorithmic advancements, leveraging tools from probability theory, optimization, and geometry.
Keywords include: Data-driven Decision-making, Experimentation, Data Value, Stochastic Optimization, Distributionally Robust Optimization, Human-AI Interaction.

Recent News
  • MIT Spotlight: Our research was featured as the main story on the MIT homepage!
  • Upcoming Talk in Raul Castro's lecture series "The Value of Data" at the University of Chicago (November 21st).
  • INFORMS 2025: I will be chairing a session and giving a talk on the value of data in decision-making and optimization.
    • Co-chairing with Lin Fan the session "Experimentation and Decision-making" featuring Omar Bennouna (MIT), Prof Omar Besbes (Columbia), Tiffany Cai (Columbia), and Prof Yassir Jedra (Imperial) (Mon Oct 27, 2:45pm, B202).
    • Presenting "Data Informativeness in Decision-Making" in Yeganeh Alimohammadi's Modern AI and Marketplaces session (Sun Oct 26, 1:15pm, B315).
    • My co-author Omar Bennouna will present our joint paper at the Data Mining and Decision Analytics Workshop on Saturday as a Best Paper finalist.
  • Our paper What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization was accepted in NeurIPS 2025! It is also finalist of the INFORMS Data Mining and Data Analytics Workshop Best Paper Award (Theoretical Track).
Papers
  • Robust Two-Stage Optimization with Covariate Data
    with Bart Van Parys & Julien Pinede.
Teaching
  • Optimization Methods, MIT 15.093/6.255 | Head Teaching Assistant
    Graduate (Masters, PhDs, MBAn, MBA), Fall 2021. (180 students)
  • Optimization Methods, MIT 15.093/6.255 | Teaching Assistant
    Graduate (Masters, PhDs, MBAn, MBA), Fall 2020. (120 students)
  • The Analytics Edge, MIT 15.071 | Guest Lecturer
    Graduate (MBA), Fall 2023. (80 students)
  • The Advanced Analytics Edge, MIT 15.072 | Guest Lecturer
    Graduate (MBAn), Fall 2023. (100 students)
  • Classes Préparatoires Instructor (Louis-le-Grand, Saint Louis, Henri IV)
    Instructor and examiner in advanced mathematics for undergraduate students of top French classes préparatoires
Service
    Reviewer
    Operations Research, Management Science, Annals of Applied Probability, NeurIPS, Automatica, INFORMS Journal on Optimization.
Talks
    What Data Enables Optimal Decisions?
    University of Chicago, "The Value of Data" lecture series.
    INFORMS Annual Meeting, October 2025, Atlanta GA
    (Panel) Workshop on Incentives for Collaborative Learning and Data Sharing, August 2025, Chicago IL
    Revenue Management and Pricing Section Conference, July 2025, New York NY
    Applied Probability Society Conference, July 2025, Atlanta GA

    From Distributional Robustness to Robust Statistics
    INFORMS Annual Meeting, October 2024, Seattle WA

    Holistic Robust Data-Driven Decisions + Robust Machine Learning
    International Research and Innovation Seminar @ UM6P, December 2023, Morocco
    INFORMS Annual Meeting, October 2023, Phoenix AZ
    CMU YinzOR Selected Flash Talk, August 2023, Pittsburgh PA (Awarded 3rd Best Flash Talk)
    SIAM Conference on Optimization, June 2023, Seattle WA
    MSOM Conference, June 2023, Montreal
    UM6P ThinkAI Hackathon, May 2023, Morocco
    MIT ORC Seminar (Best Paper Award), February 2023, Cambridge MA
    INFORMS Annual Meeting, October 2022, Indianapolis IN
    MoroccoAI Webinar, October 2022, virtual
    ICCOPT, July 2022, Bethlehem PA
    MIT ORC Student Seminar, October 2022, Cambridge MA

    Certified Robust Neural Networks: Bridging Generalization and Corruption Resistance
    INFORMS Annual Meeting Data Mining Best Paper Competition, October 2023, Phoenix AZ
    INFORMS Workshop on Data Science, October 2023, Phoenix AZ
    ICML, July 2023, Honolulu HI/virtual

    Learning and Decision-Making with Data: Optimal Formulations and Phase Transitions
    INFORMS Annual Meeting, October 2021, Anaheim CA
    MIT ORC Student Seminar, October 2021, Cambridge MA

    Learning the Minimal Representation of a Continuous State-Space Markov Decision Process from Transition Data
    INFORMS Annual Meeting Service Science Best Cluster Paper, October 2024, Seattle WA
    INFORMS Healthcare Conference, July 2021, virtual
    MSOM Conference, June 2021, virtual
    MIT ORC Student Seminar, April 2021, Cambridge MA
    INFORMS Annual Meeting, November 2020, virtual

    The Representation Power of Neural Networks
    ICLR, April 2022, virtual (poster session)
    MIT ORC Student Seminar, March 2021, Cambridge MA
    MIT SIAM Student Seminar, December 2020, Cambridge MA
The background is a typical geometric motif of Moroccan mosaic tilework. These beautiful geometric patterns, found everywhere in Morocco, date back to the 10th century. Beyond their beauty, they are facinating mathematical objects. (Credit: Zellij gallery)