About me

    I am a second-year student at the MIT Operations Research Center Master of Science, advised by Prof. Rahul Mazumder. My research interests lie at the intersection of Machine Learning, Optimization and Statistics, building new algorithms to compute interpretable estimators, and understanding their statistical performance. Prior to MIT, I earned an MS in Applied Mathematics from Ecole Polytechnique.

    Determined to develop a business-focused mindset, I led a six month Machine Learning research internship as an Equity Derivative Structurer in Societe Generale. In addition, I gained two international experiences as a Web Developer in Option, Santiago (Chile) and Teacher Assistant in Shanghai ParisTech Jiao Tong (China). Passionate about applying data-driven methods to solve complex decision-making problems, I seek challenges afforded by high-impact projects.

Working / Submitted Papers

  • Bayesian modeling for user session length prediction in music streaming.
    Dedieu, A., Mazumder, R., working paper.
  • Sparse SVM and Logistic Regression: Unified framework through mixed-integer optimization.
    Dedieu, A., Mazumder, R., working paper.
  • Error bounds for sparse classifiers in high-dimensions.
    Dedieu, A., Mazumder, R. Submitted to Artificial Intelligence and Statistics 2017.
  • Hybrid Column-and-Constraint Generation for large-scale L1-SVM.
    Dedieu, A., Mazumder, R. Submitted to Advances in Neural Information Processing System 2017
  • Subset Selection with Shrinkage: Sparse Linear Modeling when the SNR is low.
    Mazumder, R., Radchenko, P., Dedieu, A. ArXiv .

Class Projects