Scholar
Yassir Jedra
Google Scholar ID: tePNfWQAAAAJ
Imperial College London
Citations & Impact
Citations
528
H-index
11
i10-index
11
Publications
20
Co-authors
18
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Paper 'Model-free Low-rank RL with Leveraged Entrywise Matrix Estimation' accepted at NeurIPS 2024 and to be presented at EWRL 2025; 'Minimal Order Recovery through Rank-adaptive Identification' accepted at CDC 2025; 'Sub-optimality of the Separation Principle for Quadratic Control from Bilinear Observations' also accepted at CDC 2025; 'Finite Sample Identification of Partially Observed Bilinear Dynamical Systems' accepted at L4DC 2025 and selected for an oral presentation.
Research Experience
- Joining Imperial College London as an Assistant Professor within the EEE department starting 2025/2026; previously a postdoctoral researcher at LIDS, MIT, working with Devavrat Shah.
Education
- Received a BSc and MSc in Mathematics and Computer Science from ENSIMAG -- Grenoble-INP in 2015 and 2018, respectively; completed a PhD in Electrical Engineering at KTH Royal Institute of Technology, advised by Alexandre Proutiere.
Background
- Research interests broadly revolve around developing statistical and algorithmic foundations for sequential learning and control of dynamical systems under uncertainty. Specific areas include reinforcement learning, multi-armed bandits, system identification, adaptive control, and high-dimensional/causal inference.
Miscellany
- Attended ICML 2024 to present work on low-rank bandits; participated in the 2024 ESIF Economics and AI+ML meeting, discussing how to exploit observation bias to improve outcome prediction.
