Post-Doctoral Research Visit F/M Distributed Learning for Streaming Data

Post-Doctoral Research Visit F/M Distributed Learning for Streaming Data

Fonction : Post-Doctorant

Postdoctoral contract: duration of 12 to 24 months.

The default start date is November 1st, 2026 and not later than January 1st, 2027. The postdoctoral fellow will be recruited by one of the Inria Centres in France, but it is recommended that the time be shared between France and the partner’s country. The fellow has to start the contract in France, and visits must respect Inria mission rules.

The position is part of the existing Inria Associate Team project PRIDeL, a collaboration between Simula, Inria, and NYCU on real‑time distributed learning. The project will be supervised by Dr. Malcolm Egan (Inria), Dr. Hsuan‑Yan Lin (Simula), and Prof. Yu‑Chih Huang (NYCU, Taiwan).

The overall goal of the PRIDeL project is to co‑design communication‑efficient and private real‑time distributed learning in edge inference networks. The key objectives are:

• Coping with Communication Constraints on Real‑time Federated and Distributed Learning.
• Data Freshness and Personalization.
• Private, Communication‑Efficient Distributed Learning for Streaming Data.

Responsibilities:

• Develop new distributed algorithms for learning with streaming data, focusing on convergence theory and generalization error bounds or on experimental studies using large‑scale systems supported by the Grid5000 cluster.
• Formalize and incorporate data freshness into training and inference processes.
• Design the learning mechanism, communication network, or differential privacy scheme, depending on the candidate’s profile.
• Integrate developed algorithms into a holistic framework for distributed learning with streaming data in the PRIDeL project.

Qualifications:

• PhD in distributed or federated learning, learning with time‑series data, differential privacy, or communication networks for learning.
• Defended the PhD no later than December 31, 2026.
• Shown ability to work both theoretically and experimentally in the area of real‑time distributed learning.
• Preference for candidates from a scientific environment different from their PhD environment, particularly French or international candidates with a doctorate obtained abroad.

Avantages

• Partial reimbursement of public transport costs.
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT + possibility of exceptional leave (sick children, moving home, etc.).
• Possibility of teleworking after 6 months of employment and flexible organization of working hours.
• Professional equipment available (videoconferencing, loan of computer equipment, etc.).
• Social, cultural and sports events and activities.