
Tareq Si Salem · Ph.D.
Applied research: theory meets practice
Machine learning. Mathematical modeling.
Senior researcher at Huawei Paris Research Center.
طارق سي سالم ⵜⴰⵔⵉⵇ ⵙⵉ ⵙⴰⵍⴻⵎ
Research perspective
Tareq Si Salem (طارق سي سالم, ⵜⴰⵔⵉⵇ ⵙⵉ ⵙⴰⵍⴻⵎ) is a senior researcher at Huawei Paris Research Center. He earned his Ph.D. in Computer Science (2022) from Université Côte d'Azur / Inria Sophia Antipolis with Giovanni Neglia, and held research positions at Northeastern University (with Stratis Ioannidis) and TU Delft (with George Iosifidis). His work spans machine learning and mathematical modeling, focusing on learning under constraints such as privacy, safety, fairness, memory, and communication. He has published in IEEE/ACM ToN, ACM SIGMETRICS, AAAI, and IEEE INFOCOM, and won the ITC'33 Best Paper Award (2021).
- Online learning
- Time-series forecasting
- Constrained optimization
- Machine learning systems
Selected publications
All publications ↗Bandits in Flux: Dynamic Regret under Adversarial Constraints
Author: Tareq Si Salem
International Conference on Artificial Intelligence and Statistics (AISTATS), 2026
RebuttalGoal-Oriented Time-Series Forecasting: Foundation Framework Design
Authors: Luca-Andrei Fechete, Mohamed Sana, Fadhel Ayed, Nicola Piovesan, Wenjie Li, Antonio De Domenico, Tareq Si Salem (lead researcher)
The AAAI Conf. on Artificial Intelligence (AAAI), Singapore, 2026 (A*, 17.6% AR)
Online Submodular Maximization via Online Convex Optimization
Authors: Tareq Si Salem, Gözde Özcan, Iasonas Nikolaou, Evimaria Terzi, Stratis Ioannidis
The AAAI Conf. on Artificial Intelligence (AAAI), Vancouver, Canada, 2024 (A*, 23% AR)
Enabling Long-term Fairness in Dynamic Resource Allocation
Authors: Tareq Si Salem, George Iosifidis, Giovanni Neglia
ACM International Conferences on Measurement and Modeling of Computer Systems (SIGMETRICS), Orlando, Florida, USA, 2023 (A*, 15% AR)
Ascent Similarity Caching with Approximate Indexes
Authors: Tareq Si Salem, Giovanni Neglia, Damiano Carra
IEEE/ACM Transactions on Networking (ToN) (Best Paper ITC'33), 2022
GRADES: Gradient Descent for Similarity Caching
Authors: Anirudh Sabnis, Tareq Si Salem, Giovanni Neglia, Michele Garetto, Emilio Leonardi, Ramesh K. Sitaraman
IEEE International Conferences on Computer Communications (INFOCOM), 2021 (A*, 19% AR)
Mentorship
Students & interns
-
M. DOROCH
École Normale Supérieure Paris-Saclay / St. Petersburg State University. Co-supervised with EURECOM. Topic: Foundation Models for Time Series Modeling. CIFRE Ph.D., 2026–2029.
-
D. KUSMANOV
University College London, MSc Data Science and Machine Learning. Topic: Time Series Model Identification. Internship, June–September, 2026. -
A. AGUERJOUT
École Polytechnique, X2027. Topic: Time Series. Internship, June–September, 2026. -
L. FECHETE
École Polytechnique, BX 2025 → EPFL M.S. Statistics. Topic: Goal-oriented Forecasting; resulted in an AAAI A* paper (4 months, 2025).