Responsive image

Flavio du Pin Calmon

Assistant Professor

I am an Assistant Professor of Electrical Engineering at Harvard's John A. Paulson School of Engineering and Applied Sciences. Before joining Harvard I was a social good post-doctoral fellow at IBM Research in Yorktown Heights, New York. I received my Ph.D. in Electrical Engineering and Computer Science at MIT. My main research interests are information theory, inference, and statistics, with applications to privacy, fairness, machine learning, and communications engineering.

Research

My research has three intertwined goals: (i) develop theory and models that capture the fundamental limits of estimation and learning from data, (ii) construct fair and private learning algorithms with performance guarantees based on these limits, and (iii) use this methodology as a design driver for future information processing and content distribution systems. In order to achieve these goals I use theoretical tools from information theory, statistics, cryptography and machine learning.

I consider myself a scientist who is an engineer at heart, so I enjoy doing fundamental research that serves as a design driver for practical applications. I have a broad set of interests which include information theory, statistics, communications and optimization. You can find more details in the publications below.

Recent announcements

  • July, 2021 — Haewon's research featured at SEAS!

    Read more about Haewon Jeong's exciting work at the SEAS website.

  • June, 2021 — NSF-Amazon Fairness in AI Award.

    We just kicked-off the research sponsored by a recent NSF and Amazon FAI grant! Very grateful to the National Science Foundation and Amazon for supporting our work.

  • April, 2021 — Título de Honra ao Mérito da Universidade de Brasília.

    Extremely honored for receiving the inaugural Título de Honra ao Mérito (Honor to the Merit award) from the University of Brasilia (UnB), my alma mater. This new award recognizes alumni who have achieved national and/or international recognition in their field of study at UnB. I was the first alumni chosen for the award from the area of "technology and exact sciences" (i.e., engineering, math, statistics, and CS).

  • July, 2020 — Teaching commendation.

    Honored for receiving a commendation from the Harvard College's Dean of Undergraduate Education for "extraordinary teaching during extraordinary times." Signals & Communications (ES 156) is more important than ever!

  • June, 2020 — Amazon Research Award.

    Alexa, thank you for sponsoring our work with an Amazon Research Award!

  • September, 2019 — NSF Grants.

    I am once again grateful to National Science Foundation for supporting our work on privacy with an NSF Medium grant and in fair machine learning with an NSF Eager grant.

  • March, 2019 — Google Faculty Research Award.

    Ok Google, thank you so very much for your generous gift (see under "Machine Learning and Data Mining").

  • Dec, 2018 — NSF CAREER Award!

    I am very grateful for the support of the National Science Foundation for our research on information-theoretic foundations of fair machine learning (check out this GSAS feature). You can learn more details about the award at the Harvard SEAS website.

  • Nov, 2018 —IBM Open Collaborative Research Award.

    Thank you IBM!

  • April, 2018 —Lemann Brazil Research Fund Award.

    We are excited to organize a course on ML at FEEC/Unicamp in August 2019! You can find more details here.

  • Research Group

    I am very fortunate to work with an amazing group of students, post-docs, and visitors.

    Current Members

  • Hao Wang (PhD, G5)
  • Hsiang Hsu (PhD, G4)
  • Wael Alghmadi (PhD, G4)
  • Madeleine Barowsky (PhD, G2)
  • Shahab Asoodeh (SEAS Post-Doc)
  • Haewon Jeong (SEAS Post-Doc)
  • Alumni

  • Berk Ustun (Former CRCS Post-Doc, next stop Google then faculty at UCSD)
  • Javier Zazo (Former CRCS Post-Doc, next stop Microsoft Research)
  • Papers

    An (almost) up-to-date list of publications can be found on Google Scholar.

    The list below may be outdated.

    Pre-prints

  • Bottleneck Problems: Information and Estimation-Theoretic View
    S. Asoodeh, F.P. Calmon
  • Three Variants of Differential Privacy: Lossless Conversion and Applications
    S. Asoodeh, J. Liao, F. P. Calmon, O. Kosut, and L. Sankar
  • Generalizing Correspondence Analysis for Applications in Machine Learning
    H. Hsu, S. Salamatian, and F. P. Calmon
  • Hiding symbols and functions: New metrics and constructions for information-theoretic security
    F. P. Calmon, M. Médard, M. Varia, K. R. Duffy, M. M. Christiansen, and L. M. Zeger
  • 2020

  • To Split or Not to Split: The Impact of Disparate Treatment in Classification
    H. Wang, H. Hsu, M. Diaz, and F. P. Calmon
    Symp. on the Foundations of Responsible Computing, 2020
  • Predictive Multiplicity in Classification
    C. T. Marx, F. P. Calmon, and B. Ustun
    Int. Conf. on Machine Learning (ICML), 2020
  • Differentially private federated learning: An information-theoretic perspective
    S. Asoodeh and F. P. Calmon
    International Workshop on Federated Learning for User Privacy and Data Confidentiality (ICML-FL), 2020
  • Model projection: Theory and applications to fair machine learning
    W. Alghamdi, S. Asoodeh, H. Wang, F. P. Calmon, D. Wei, and K. N. Ramamurthy
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2020, pp. 2711–2716
  • Privacy amplification of iterative algorithms via contraction coefficients
    S. Asoodeh, M. Diaz, and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2020, pp. 896–901
  • A better bound gives a hundred rounds: Enhanced privacy guarantees via f-divergences
    S. Asoodeh, J. Liao, F. P. Calmon, O. Kosut, and L. Sankar
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2020, pp. 920–925.
  • Obfuscation via information density estimation
    H. Hsu, S. Asoodeh, and F. P. Calmon
    Int. Conf. on Artificial Intelligence and Statistics (AISTATS), 2020
  • Optimized score transformation for fair classification
    D. Wei, K. N. Ramamurthy, and F. P. Calmon
    Int. Conf. on Artificial Intelligence and Statistics (AISTATS), 2020
  • On the robustness of information-theoretic privacy measures and mechanisms
    M. Diaz, H. Wang, F. P. Calmon, and L. Sankar
    IEEE Trans. Inf. Theory, vol. 66, no. 4, pp. 1949–1978, April 2020.
  • Privacy-preserving image sharing via sparsifying layers on convolutional groups
    S. Ferdowsi, B. Razeghi, T. Holotyak, F. P. Calmon, and S. Voloshynovskiy
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020, pp. 2797–2801.
  • High-SNR performance in Gaussian-class fading
    F. R. A. Parente, F. P. Calmon, and J. C. S. Santos Filho
    IEEE International Conference on Communications (ICC)
  • Maximal α-Leakage and its Properties
    J. Liao, L. Sankar, O. Kosut, F.P. Calmon
    IEEE Conference on Communications and Network Security (CNS)
  • 2019

  • Privacy with estimation guarantees
    H. Wang, L. Vo, F. P. Calmon, M. Médard, K. R. Duffy, and M. Varia
    IEEE Trans. Inf. Theory vol. 65, no. 12, pp. 8025–8042, Dec 2019.
  • Tunable measures for information leakage and applications to privacy-utility tradeoffs
    J. Liao, O. Kosut, L. Sankar, and F. P. Calmon
    IEEE Trans. Inf. Theory , vol. 65, no. 12, pp. 8043–8066, Dec 2019.
  • Confronting data sparsity to identify potential sources of zika virus spillover infection among primates
    S. Majumdar, B. Han, F. P. Calmon, B. Glicksberg, R. Horesh, A. Kumar, A. Perer, E. V. Marschall, D. Wei, A. Mojsilović, and K. Varshney
    Epidemics. 2019 Jun;27:59-65.
  • On the multiplicity of predictions in classification
    C. Marx, F. P. Calmon, and B. Ustun
    NeurIPS Workshop on Human-Centric Machine Learning, 2019.
  • Discovering information-leaking samples and features,
    H. Hsu, S. Asoodeh, and F. P. Calmon
    NeurIPS Workshop on Privacy and Machine Learning, 2019.
  • An Information-Theoretic View of Generalization via Wasserstein Distance
    H. Wang, M. D. Torres, J. C. S. S. S. Filho, and F. P. Calmon,
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2019
  • Information-theoretic privacy watchdogs
    H. Hsu, S. Asoodeh, and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2019
  • Mutual information as a function of moments
    W. Algahmdi and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2019
  • Robustness of maximal α-leakage to side information
    J. Liao, L. Sankar, O. Kosut, and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2019
  • Repairing without retraining: Avoiding disparate impact with counterfactual distributions
    H. Wang, B. Ustun, and F. P. Calmon
    ICML 2019
  • Correspondence Analysis Using Neural Networks
    H. Hsiang, S. Salamatian, F. P. Calmon
    The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS).
  • 2018

  • Avoiding disparate impact with counterfactual distributions
    H. Wang, B. Ustun, F. P. Calmon
    NeurIPS Workshop on Ethical, Social and Governance Issues in AI.
  • Correspondence analysis of government expenditure patterns
    H. Hsu, F. P. Calmon, J. C. S. Santos Filho, A. P. Calmon, and S. Salamatian
    NeurIPS Workshop on Machine Learning for the Developing World (ML4D).
  • Data Pre-Processing for Discrimination Prevention: Information-Theoretic Optimization and Analysis
    F. P. Calmon, D. Wei, B. Vinzamuri, K. N. Ramamurthy, and K. R. Varshney
    IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 5, pp. 1106-1119, Oct. 2018.
  • The utility cost of robust privacy guarantees
    H. Wang, M. Diaz, F. P. Calmon, and L. Sankar
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 706-710, 2018
  • On the direction of discrimination: An information-theoretic analysis of disparate impact in machine learning
    H. Wang, B. Ustun, and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 1216-1220, 2018
  • Generalizing Bottleneck Problems
    H. Hsu, S. Asoodeh, S. Salamatian, and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 531-535, 2018
  • A Tunable Measure for Information Leakage
    J. Liao, O. Kosut, L. Sankar, and F. P. Calmon
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 701-705, 2018
  • Hypothesis testing under mutual information privacy constraints in the high privacy regime
    J. Liao, L. Sankar, V. Y. F. Tan, and F. P. Calmon
    IEEE Trans. Inf. Forensics Security, vol. 13, no. 4, pp. 1058–1071, 2018
  • Strong data processing inequalities for input constrained additive noise channels
    F. P. Calmon, Y. Polyanskiy, and Y. Wu
    IEEE Trans. Inf. Theory, vol. 64, no. 3, pp. 1879-1892, 2018
  • 2017

  • Optimized pre-processing for discrimination prevention
    F. P. Calmon, D. Wei, B. Vinzamuri, K. N. Ramamurthy, and K. R. Varshney
    NIPS 2017
  • An estimation-theoretic view of privacy
    H. Wang and F. P. Calmon
    Proc. 55th Annual Allerton Conference on Communication, Control, and Computing, 2017
  • Principal inertia components and applications
    F. P. Calmon, A. Makhdoumi, M. Médard, M. Varia, M. Christiansen, and K. R. Duffy
    IEEE Trans. Inf. Theory, vol. 63, no. 8, pp. 5011–5038, 2017
  • Mutual outage probability
    F. P. Calmon, Á. A. M. de Medeiros, and M. D. Yacoub
    IEEE Trans. Wireless Commun., vol. 16, no. 5, pp. 3138–3150, 2017
  • Hypothesis testing under maximal leakage privacy constraints
    J. Liao, L. Sankar, F. P. Calmon, and V. Y. Tan
    IEEE Int. Symp. on Inf. Theory (ISIT), 2017, pp. 779–783
  • Prior to 2017

  • Correcting forecasts with multifactor neural attention
    M. Riemer, A. Vempaty, F. P. Calmon, F. Heath, R. Hull, and E. Khabiri
    ICML 2016
  • Hypothesis testing in the high privacy limit
    J. Liao, L. Sankar, V. Y. F. Tan, and F. P. Calmon
    Proc. 54th Annual Allerton Conference on Communication, Control, and Computing, 2016
  • Multi-user guesswork and brute force security
    M. M. Christiansen, K. R. Duffy, F. P. Calmon, and M. Médard
    IEEE Trans. Inf. Theory, vol. 61, no. 12, pp. 6876 – 6886, Dec 2015
  • Information-theoretic metrics for security and privacy
    F. P. Calmon
    Ph.D. Thesis, MIT, 2015
  • Managing your private and public data: Bringing down inference attacks against your privacy
    S. Salamatian, A. Zhang, F. Calmon, S. Bhamidipati, N. Fawaz, B. Kveton, P. Oliveira, and N. Taft
    IEEE J. Sel. Topics Signal Proces., vol. 9, no. 7, pp. 1240–1255, 2015
  • Fundamental limits of perfect privacy
    F. P. Calmon, A. Makhdoumi, and M. Médard
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 1796–1800, 2015
  • Strong Data Processing Inequalities in Power-Constrained Gaussian Channels
    F. P. Calmon, Y. Polyanskiy, and Y. Wu
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 2558–2562, 2015
  • Forgot your password: Correlation dilution
    A. Makhdoumi, F. P. Calmon, and M. Médard
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), pp. 2944–2948, 2015
  • An exploration of the role of principal inertia components in information theory
    F. P. Calmon, M. Varia, and M. Médard
    Proc. IEEE Inf. Theory Workshop, Nov. 2014
  • On information-theoretic metrics for symmetric-key encryption and privacy
    F. P. Calmon, M. Varia, and M. Médard
    Proc. 52nd Annual Allerton Conference on Communication, Control, and Computing, 2014
  • Bounds on inference
    F. P. Calmon, M. Varia, M. Médard, M. M. Christiansen, K. R. Duffy, and S. Tessaro
    Proc. 51st Annual Allerton Conference on Communication, Control, and Computing, 2013
  • Brute force searching, the typical set and guesswork
    M. M. Christiansen, K. R. Duffy, F. P. Calmon, and M. Médard
    Proc. IEEE Int. Symp. on Inf. Theory (ISIT), 2013, pp. 1257–1261
  • Guessing a password over a wireless channel (on the effect of noise non-uniformity)
    M. M. Christiansen, K. R. Duffy, F. P. Calmon, and M. Médard
    Proc. Asilomar Conference on Signals, Systems and Computers, 2013, pp. 51–55
  • How to hide the elephant-or the donkey-in the room: Practical privacy against statistical inference for large data
    S. Salamatian, A. Zhang, F. P. Calmon, S. Bhamidipati, N. Fawaz, B. Kveton, P. Oliveira, and N. Taft
    Proc. IEEE GlobalSIP, 2013
  • Multi-path TCP with network coding for mobile devices in heterogeneous networks
    J. Cloud, F. P. Calmon, W. Zeng, G. Pau, L. M. Zeger, and M. Médard
    Proc. IEEE 78th Vehicular Technology Conference, 2013, pp. 1–5
  • A framework for privacy against statistical inference
    F. P. Calmon and N. Fawaz
    Proc. 50th Annual Allerton Conference on Communication, Control, and Computing, 2012
  • Speeding multicast by acknowledgment reduction technique (SMART) enabling robustness of QoE to the number of users
    A. Rezaee, F. P. Calmon, L. M. Zeger, and M. Médard
    IEEE J. Sel. Areas Commun., vol. 30, no. 7, pp. 1270 –1280, Aug. 2012
  • Lists that are smaller than their parts: A coding approach to tunable secrecy
    F. P. Calmon, M. Médard, L. Zeger, J. Barros, M. M. Christiansen, and K. R. Duffy
    Proc. 50th Annual Allerton Conference on Communication, Control, and Computing, 2012
  • Equivalent models for multi-terminal channels
    F. P. Calmon, M. Médard, and M. Effros
    Proc. IEEE Inf. Theory Workshop, Oct. 2011.
  • MRCS – selecting maximal ratio combined signals: a practical hybrid diversity combining scheme
    F. P. Calmon and M. D. Yacoub
    IEEE Trans. Wireless Commun., vol. 8, no. 7, pp. 3425–3429, Jul. 2009
  • A general exact formulation for the outage probability in interference-limited systems
    F. P. Calmon and M. D. Yacoub
    Proc. IEEE Global Telecommunications Conference (GLOBECOM), Nov. 2008
  • Patents

    Teaching

    Fall 2021: Information Theory (ES 250)

    Spring 2021: Signals & Communications (ES 156)

    Fall 2020: On parental leave from teaching

    Spring 2020: Signals & Communications (ES 156)

    Fall 2019: Information Theory (ES 250)

    Spring 2019: Signals and Systems (ES 156)

    Spring 2018: Signals and Systems (ES 156)

    Fall 2017: Information Theory (ES 250)

    Contact

    Email: flavio (at) seas (dot) harvard (dot) edu

    Office:
    Science & Engineering Complex
    150 Western Ave
    Office 3.306
    Allston, MA 02134