# jemdoc: menu{MENU}{index.html}
= Samir M. Perlaza | Princeton University | Electrical and Computer Engineering
~~
{}{img_left}{Images/Perlaza_PortraitLong6.jpeg}{Portrait of Samir M. Perlaza}{214}{300}
*Samir M. Perlaza *\n
Permanent Member of the Scientific Staff at [https://www.inria.fr INRIA] \n
Visiting Research Collaborator\n
[https://ece.princeton.edu Department of Electrical and Computer Engineering] \n
[http://www.princeton.edu Princeton University]\n
Princeton, New Jersey, USA
~~~
~~~
{Contact}
INRIA \n
[https://www.inria.fr/fr/centre-inria-sophia-antipolis-mediterranee Centre de Recherche de Sophia Antipolis - Méditerranée ] \n
2004, route des Lucioles BP 93, 06902 Sophia Antipolis Cedex \n
Équipe [https://team.inria.fr/neo/team-members/ NEO], Bâtiment Lagrange, Office: L137 \n
[samir.perlaza@inria.fr]
~~~
== Research
I am interested in theoretical and practical aspects of *game theory* and *information theory*. The application domains that motivate my research include *statistical machine learning*, *decision making*, *communication systems*, and *electric power systems*.
=== Selected Research Areas
~~~
*Statistical Empirical Risk Minimization and Generalization Capabilities of Machine Learning Algorithms*
- I am interested in the *empirical risk minimization* (ERM) problem when the optimization domain is a given set of probability measures over the set of models. A solution to this problem is a probability measure from which models can be sampled from to perform a machine learning task, e.g., a classification or a regression. A popular probability measure that arises from the ERM, subject to particular regularizations, is the *Gibbs probability measure*, which leads to the well-known Gibbs algorithm in statistical machine learning. The key challenge in this problem is the inclusion of previous knowledge about the models via regularizations of the ERM to enhance the generalization capabilities of machine learning algorithms. My research focuses on the study of the statistical properties of the random variables representing the training loss and test loss, when models are sampled from probability measures that are solutions to ERM problems subject to particular regularizations. The main feature of this research effort is that contrary to the main stream in the community, *this analysis is made for fixed training datasets*, which provides new and insightful mathematical tools for the analysis of generalization capabilities of machine learning algorithms.
- *Selected *(Recent)* Results:*
-- [https://hal.archives-ouvertes.fr/hal-03560072/document ``*Empirical Risk Minimization with Relative Entropy Regularization*''], with Gaetan Bisson, Iñaki Esnaola, Alain Jean-Marie, Stefano Rini. \n
Research Report, INRIA, No. RR-9454, Sophia Antipolis, France, Feb., 2022.
-- [https://hal.science/hal-04258765/document ``*Empirical Risk Minimization with f-Divergence Regularization in Statistical Learning*''], with Francisco Daunas, Iñaki Esnaola, and H. Vincent Poor. \n
Research Report, INRIA, No. RR-9521, Sophia Antipolis, France, Oct., 2023".
-- [https://hal.science/hal-04181971/document ``*The Worst-Case Data-Generating Probability Measure*''], with Xinying Zou, Iñaki Esnaola, and Eitan Altman. \n
Research Report, INRIA, No. RR-9515, Sophia Antipolis, France, Aug., 2023".
~~~
~~~
*Machine Learning and Decision Making with Noisy Observations*
- Recently, we have introduced a new formulation of zero-sum games (ZSG), which is particularly suited for studying decision making problems in which decision makers observe each other decisions subject to some degree of distorsion. Such a distorsion is modelled using the notion of *channel*, as in the realm of information theory. This provide the flexibility to consider effects such as quantization due to data acquisition via digital systems, additive noise due to privacy concerns, etc. Under these conditions, we have shown that the equilibrium of this game always exists and is often different from the Nash and Stackelberg equilibria. My research focuses on the analysis of the efect of the channel in the behavior of the decision makers. More specifically, my objective is to quantify, using information measures, the benefit or the loss for a given player due the distorsion in its observations.
- *Selected *(Recent)* Results:*
-- [https://hal.science/hal-03838009/document ``*2 × 2 Zero-Sum Games with Commitments and Noisy Observations*''], with Ke Sun and Alain Jean-Marie. \n
Research Report, INRIA, No. RR-9505, Sophia Antipolis, France, May., 2023.
~~~
== Teaching
- INFOXXXX - [http://www-sop.inria.fr/members/Samir.Perlaza/ENS-Course2022.html *Foundations of Data Analytics*] at ENS de Lyon, (*under evaluation* for) 2024 - 2025
- INFO5147 - [http://www-sop.inria.fr/members/Samir.Perlaza/ENS-Course2020.html *Selected Topics in Information Theory*] at ENS de Lyon, 2020 - 2021
- INFO5147 - [http://www-sop.inria.fr/members/Samir.Perlaza/ENS-Course2019.html *Selected Topics in Information Theory*] at ENS de Lyon, 2019 - 2020
- INFO5147 - [http://www-sop.inria.fr/members/Samir.Perlaza/ENS-Course2016.html *Network Information Theory*] at ENS de Lyon, 2016-2017.
== Academic Appointments
- *Permanent Member of the Scientific Staff*, INRIA, Sophia Antipolis, France. Jan. 2020 - present
- *Visiting Research Collaborator*, Department of Electrical and Computer Engineering, Princeton University, Princeton NJ, Jan. 2013 - present
- *Associate Researcher*, Université de la Polynésie Française, Laboratoire de Géométrie Algébrique et Applications à la Théorie de l’Information (GAATI), Faaa, French Polynesia, May 2021 - present
- Permanent Member of the Scientific Staff, INRIA, Lyon, France. Dec. 2013 - Jan. 2020
- Postdoctoral Associate, Princeton University, Princeton NJ, Jan. 2012 - Dec. 2013
- Postdoctoral Associate, Alcatel-Lucent Chair at Supélec, Orsay, France. Jul. 2011 - Dec. 2011
- Research Engineer, France Télécom - Orange, Issy les Moulineaux, France, Jan. 2008 - Jan. 2011
== Education
- HDR, Université de Lyon I and INSA de Lyon, France, 2021
- Ph.D., Télécom ParisTech, Paris, France, 2011
- MSc., EURECOM, Sophia Antipolis, France, 2007
- BSc. Universidad del Cauca, Popayán, Colombia, 2005
== Editorial Boards
- Editor, IEEE Transactions on Communications, 2017 - 2022
- Editor, IET Smart Grids, 2018 - 2021
- Associate Editor, Frontiers in Communications and Networks, 2020 - 2022
- Guest Editor of the IEEE Internet of Things Journal, Special Issue on ``Artificial Intelligence Powered Edge Computing for the Internet of Things'', 2020
== International Research Projects
- Principal (French) Investigator of EU funded H2020-MSCA-RISE-2019 project: "Testing and Evaluating Sophisticated information and communication Technologies for enaBling scalablE smart griD Deployment (TESTBED2)". Grant Agreement no. 872172. [https://www.testbed2.org (web)]
- Principal (French) Investigator of EU funded ERA-NET-MED-2015 project: "COMMunication systems with renewable Energy micro-griD (COM-MED)". EU Project locally handled by ANR under Grant Agreement ANR-15-NMED-0009-03. [http://commed.ucy.ac.cy/index.html (web)]
- Principal Investigator of H2020 project CYBERNETS under EU Grant agreement 659316. [http://cybernets.inria.fr (web)]
== Acknowledgments and Awards
- INRIA Exploratory Action ([https://www.inria.fr/en/idem *Information and Decision Making - IDEM*]) to characterize the interplay between data acquisition and information processing in decentralized decision making by bringing together tools from information theory and game theory. Action starts in 2022
- Prime d’encadrement Doctoral et de Recherche (PEDR), granted by INRIA in 2021
- Fellowship of The Finnish Society of Sciences and Letters. Host: School of Energy Systems at Lappeenranta University of Technology, Finland. Apr. 2019
- Fellowship "Make our Planet Great Again" of the Embassy of France in the United States of America, received jointly with Prof. Ali Tajer in 2017
- Prime d’encadrement Doctoral et de Recherche (PEDR), granted by INRIA in 2014
- *Marie Sklodowska-Curie Action (MSCA) Fellow*. Individual Fellowship, Class of 2015
- IEEE Senior Member, 2015.
- Best Student Paper Award in the IEEE Intl. Conf. on Cognitive Radio Oriented Wireless Networks and Communications (CROWNCOM)), 2009
- *Alban Fellow*. the European Commission Programme of High Level Scholarships for Graduate Students from Latin America. Grant E06M101130CO.
- Baccalaureate Honoris Causa granted by Colegio Nacional de Bachillerato - Instituto Técnico on behalf of the Ministry of Education of Colombia. Santander de Quilichao, Colombia, December 2000.
- City Council Agreement No. 028 of 1999 to create the award "*Ciudad de los Samanes - Samir Alberto Medina Perlaza*" in Santander de Quilichao, Colombia. This award is given to the top-ranked students in the national exams to access higher education in a ceremony held every year at the City Hall since 1999.