Mario Diaz

Research Associate
Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas (IIMAS)
Universidad Nacional Autónoma de México (UNAM)
Curriculum Vitae / Google Scholar Profile / Publons Profile


Interests

My current research mainly focuses on data privacy, information theory and theoretical
machine learning. I also keep a research stream on random matrices and their applications.


Publications and Preprints

Journal Papers

  1. To split or not to split: the impact of disparate treatment in classification
    H. Wang, H. Hsu, M. Diaz and F. Calmon
    IEEE Transactions on Information Theory, accepted for publication
    DOI:10.1109/TIT.2021.3075415
     
  2. On the robustness of information-theoretic privacy measures and mechanisms
    M. Diaz, H. Wang, F. Calmon and L. Sankar
    IEEE Transactions on Information Theory, 2020
    DOI:10.1109/TIT.2019.2939472
     
  3. On the global fluctuations of block Gaussian matrices
    M. Diaz, J. Mingo and S. Belinschi
    Probability Theory and Related Fields, 2020
    DOI:10.1007/s00440-019-00925-1
     
  4. Estimation efficiency under privacy constraints
    S. Asoodeh, M. Diaz, F. Alajaji and T. Linder
    IEEE Transactions on Information Theory, 2019
    DOI:10.1109/TIT.2018.2865558
     
  5. On the capacity of block multiantenna channels
    M. Diaz and V. Pérez-Abreu
    IEEE Transactions on Information Theory, 2017
    DOI:10.1109/TIT.2017.2712711
     
  6. Information extraction under privacy constraints
    S. Asoodeh, M. Diaz, F. Alajaji and T. Linder
    Information, 2016
    DOI:10.3390/info7010015

Conference Papers

  1. Neural network-based estimation of the MMSE
    M. Diaz, P. Kairouz, J. Liao and L. Sankar
    IEEE International Symposium on Information Theory (ISIT), 2021
    Accepted for presentation
     
  2. The Impact of Split Classifiers on Group Fairness
    H. Wang, H. Hsu, M. Diaz and F. Calmon
    IEEE International Symposium on Information Theory (ISIT), 2021
    Accepted for presentation
     
  3. Privacy amplification of iterative algorithms via contraction coefficients
    S. Asoodeh, M. Diaz and F. Calmon
    IEEE International Symposium on Information Theory (ISIT), 2020
    DOI:10.1109/ISIT44484.2020.9174133
     
  4. On the α-loss landscape in the logistic model
    T. Sypherd, M. Diaz, L. Sankar and G. Dasarathy
    IEEE International Symposium on Information Theory (ISIT), 2020
    DOI:10.1109/ISIT44484.2020.9174356
     
  5. A tunable loss function for binary classification
    T. Sypherd, M. Diaz, L. Sankar and P. Kairouz
    IEEE International Symposium on Information Theory (ISIT), 2019
    DOI:10.1109/ISIT.2019.8849796
     
  6. An information-theoretic view of generalization via Wasserstein distance
    H. Wang, M. Diaz, JCS Santos Filho and F. Calmon
    IEEE International Symposium on Information Theory (ISIT), 2019
    DOI:10.1109/ISIT.2019.8849359
     
  7. The utility cost of robust privacy guarantees
    H. Wang, M. Diaz, F. Calmon and L. Sankar
    IEEE International Symposium on Information Theory (ISIT), 2018
    DOI:10.1109/ISIT.2018.8437735
     
  8. Privacy-aware guessing efficiency
    S. Asoodeh, M. Diaz, F. Alajaji and T. Linder
    IEEE International Symposium on Information Theory (ISIT), 2017
    DOI:10.1109/ISIT.2017.8006629
     
  9. On the symmetries and the capacity achieving input covariance matrices of multiantenna channels
    M. Diaz
    IEEE International Symposium on Information Theory (ISIT), 2016
    DOI:10.1109/ISIT.2016.7541464

Preprints

  1. Fluctuations for matrix-valued Gaussian processes
    M. Diaz, A. Jaramillo and J.C. Pardo
    Submitted to Annales de l'institut Henri Poincare (B) Probability and Statistics
    arXiv:2001.03718


Teaching


Miscellaneous Academic Activities

Last update: May 2021