Tareq Si Salem | Ph.D. Student

• I am currently visiting Embedded and Networked Systems (ENS) group at TU Delft, Netherlands. My advisor during this visit is Dr. George Iosifidis. My current research focus is fairness and online learning.

• I started my Ph.D. in October, 2019 and my Ph.D. advisor is Dr. Giovanni Neglia.

• I expect to graduate in October 1st, 2022.

More details are available in my CV.

Modeling and online learning algorithms for various network-related problems, with a special focus on caching and in-network computing.

Under Submission

• No-Regret Caching via Online Mirror Descent [arXiv]
  Tareq Si Salem, Giovanni Neglia and Stratis Ioannidis.
  

• Ascent Similarity Caching with Approximate Indexes [arXiv]
  Tareq Si Salem, Giovanni Neglia and Damiano Carra.
  

• Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees [arXiv]
  Tareq Si Salem, Gabriele Castellano, Giovanni Neglia, Fabio Pianese, and Andrea Araldo.

Journals

• GRADES: Gradient Descent for Similarity Caching
  Anirudh Sabnis, Tareq Si Salem, Giovanni Neglia, Michele Garetto, Emilio Leonardi, and Ramesh K. Sitaraman.
  IEEE/ACM Transactions on Networking, 2022.
  

• Online Caching Networks with Adversarial Guarantees [preprint] [code]
  Yuanyuan Li, Tareq Si Salem, Giovanni Neglia, and Stratis Ioannidis.
  Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2022 (SIGMETRICS 2022).

Conferences

• AÇAI: Ascent Similarity Caching with Approximate Indexes (best paper award) [preprint]
  Tareq Si Salem, Giovanni Neglia and Damiano Carra.
  International Teletraffic Congress (ITC 33), Aug. 31st - Sep. 3rd 2021.
  

• Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees [preprint]
  Tareq Si Salem, Gabriele Castellano, Giovanni Neglia, Fabio Pianese, and Andrea Araldo.
  Mediterranean Communication and Computer Networking Conference (MedComNet 2021), June 15-17, 2021.

• No-Regret Caching via Online Mirror Descent [preprint] [extended]
  Tareq Si Salem, Giovanni Neglia, and Stratis Ioannidis.
  IEEE International Conference on Communications (ICC 2021), June 14-23, 2021.

• GRADES: Gradient Descent for Similarity Caching [preprint] [dataset]
  Anirudh Sabnis, Tareq Si Salem, Giovanni Neglia, Michele Garetto, Emilio Leonardi, and Ramesh K. Sitaraman.
  IEEE International Conference on Computer Communications (INFOCOM 2021), May 10-13, 2021.

• AÇAI: Ascent Similarity Caching with Approximate Indexes. [slides]

• Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees. [video] [slides]

• No-Regret Caching via Online Mirror Descent. [video] [slides]

• Best paper award at ITC-33. [award]

• Prix d'excellence d'Université Côte d'Azur. [award]

• Optimization for Machine Learning (2020-2021)
  Duration: 6H (2 lectures).

• Distributed Optimization and Games (2019-2020)
  Duration: 3H (1 lecture).