Papers Published: 'Low-Cost Privacy-Aware Decentralized Learning' accepted for publication in Proceedings on Privacy Enhancing Technologies 2025.3; 'Boosting Asynchronous Decentralized Learning with Model Fragmentation' accepted for oral presentation at ACM Web Conference 2025; 'Fair Decentralized Learning' accepted for IEEE SaTML 2025; 'Revisiting Ensembling in One-Shot Federated Learning' accepted as a poster at NeurIPS 2024; 'Noiseless Privacy-Preserving Decentralized Learning' accepted for publication in Proceedings on Privacy Enhancing Technologies 2025.1; Received Doc.Mobility Grant 2024 from EPFL.
Research Experience
Summer 2025 Research Intern at Microsoft Research Cambridge, working on deterministic security guardrails for autonomous AI agents; Recently completed a research visit at the Camera Culture Group of the MIT Media Lab, supervised by Prof. Ramesh Raskar, focusing on enabling collaborative AI in open decentralized networks.
Education
Ph.D. in Computer Science, École Polytechnique Fédérale de Lausanne (EPFL); Visiting Ph.D. in Computer Science, Massachusetts Institute of Technology (MIT); B.Tech. in Computer Science and Engineering, Indian Institute of Technology (IIT) Mandi; Exchange Student in Computer Science, RWTH Aachen University.
Background
Research Interests: Distributed Systems, Artificial Intelligence, Machine Learning, Decentralized Learning, Privacy and Security. Professional Field: Computer Science. Bio: Rishi Sharma is a Ph.D. candidate at the Scalable Computing Systems Lab at EPFL, under the supervision of Prof. Anne-Marie Kermarrec. His research focuses on designing efficient and privacy-preserving systems for Decentralized and Federated Learning.