• Ph.D.

    Massachusetts Institute of Technology (RA, TA)

    Thesis topic: strongly Rayleigh measures for machine-learning

  • Master of Science 2016

    Massachusetts Institute of Technology (RA)

    Thesis topic: learning and enforcing diversity constraints with Determinantal Point Processes

  • Master of Science 2014

    Ecole polytechnique (France)

    Math & computer science


  • Exponentiated Strongly Rayleigh Distributions, Zelda Mariet, Suvrit Sra, Stefanie Jegelka (NeurIPS 2018)
  • Maximizing Induced Cardinality Under a Determinantal Point Process, Jennifer Gillenwater, Alex Kulesza, Sergei Vassilvtiskii, Zelda Mariet (NeurIPS 2018)
  • Foundations of Sequence-to-Sequence Modeling for Time Series, Vitaly Kuznetsov, Zelda Mariet* (preprint, 2018)
  • Learning DPPs by Sampling Inferred Negatives, Zelda Mariet, Mike Gartrell, Suvrit Sra (preprint, 2018) (R2L workshop, NeurIPS 2018)
  • Elementary Symmetric Polynomials for Optimal Experimental Design, Zelda Mariet, Suvrit Sra (NIPS 2017)  [also contributed talk @ DISCML workshop]
  • Kronecker Determinantal Point Processes, Zelda Mariet, Suvrit Sra (NIPS 2016)
  • Learning and enforcing diversity with Determinantal Point Processes, Zelda Mariet (S.M. Thesis, 2016)
  • Diversity Networks: Neural Network Compression Using Determinantal Point Processes, Zelda Mariet, Suvrit Sra (ICLR 2016)
  • Outlier Detection in Heterogeneous Datasets using Automatic Tuple Expansion, Clement Pit–Claudel, Zelda Mariet, Rachael Harding, Samuel Madden
    (Technical Report, 2016)
  • Fixed-point algorithms for learning determinantal point processes, Zelda Mariet, Suvrit Sra (ICML 2015)

Additional research experiences

  • 2017: Internship, Google Research and Machine Intelligence, NYC, New-York
    Theory and algorithms for high-dimensional time-series predictions.
  • 2016: Internship, Google Maps, Mountain View, California
    Work on ranking problems.
  • 2014: Internship, Keio University (慶應義塾大学), Yokohama, Japan
    Research in Hagiwara Lab (萩原研究室) on early pruning in neural networks
  • 2013: Internship, Bouygues Telecom, Paris, France
    RDF modeling & real-time analysis of the 4G network
  • 2013: Undergraduate research, Ecole polytechnique (France)
    Expansion of the DPLL module of the proof-search engine Psyche


  • Fall 2016: TA for MIT’s graduate Machine-Learning class (6.867)
  • 2011: Teacher, GEPPM (France) Taught physics+math classes for a non-profit to help underprivileged students to get a higher education