Working Papers

• Exploiting Observation Bias in Matrix Completion
  (α - β) : Y. Jedra, S. Mann, C. Park, D. Shah
  (In preparation)  [arxiv]

Publications

• Model free Low-rank RL via  Leveraged Entry-wise Matrix  Estimation
  S. Stojanovic*, Y. Jedra* , A. Proutiere
  To appear in Advances of Neural Information Processing Systems 37 (NeurIPS) 2024
  
  

• Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery
  Y. Jedra*, W. Reveillard*,  S. Stojanovic*,  A. Proutiere
  Proceedings of the 41st International Conference on Machine Learning (ICML) 2024  [proc]

• Learning Optimal Antenna Tilt: Control Policies: A Contextual Linear Bandit Approach
  F. Vanilla, A. Proutiere, Y. Jedra,  J. Jeong
  IEEE Transactions on Mobile Computing 2024  [IEEE Xplore] [arxiv]
  (a conference version was presented at IEEE INFOCOM 2022)
  
  

• Best Policy Identification in Linear MDPs
  J. Taupin*, Y. Jedra*,  A. Proutiere
  59th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2023  [IEEE Xplore]
  (A preliminary version has been presented at EWRL 2023)

• Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
  S. Stojanovic*, Y. Jedra*, A. Proutiere
  Advances of Neural Information Processing Systems 36 (NeurIPS), 2023.   [link] 

• A tutorial on the non-asymptotic theory of System Identification
  I. Ziemann, A. Tsiamis, B. Lee, Y. Jedra, N. Matni, G. J. Pappas
  Tutorial paper at the IEEE 62th Conference on Decision and Control (CDC), 2023.  [arxiv]
  
  

• Nearly Optimal Latent State Decoding in Block MDPs
  (α - β) : Y. Jedra*, J. Lee*,  A. Proutiere,  S. Yun  
  26th International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.  [proc.]
  
  

• Finite-time Identification of Linear Systems: Fundamental Limits and Optimal Algorithms
  Y. Jedra, A. Proutiere.   
  IEEE Transactions on Automatic Control, 2023.  [IEEE Xplore]
  
  

• Minimal Expected Regret in Linear Quadratic Control
  Y. Jedra, A. Proutiere.  
  25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.  [arxiv]
  
  

• Optimal Best-arm Identification in Linear Bandits
  Y. Jedra, A. Proutiere.  
  Advances of Neural Information Processing Systems 33 (NeurIPS), 2020. [proc.]
  
  

• Finite-time Identification of Stable Linear Systems: Optimality of the Least Squares Estimator
  Y. Jedra, A. Proutiere.
  IEEE 59th Conference on Decision and Control (CDC), 2020. [doi] [arxiv]
  
  

• Optimal Algorithms for Multiplayer Multi-armed Bandits
  P. A.  Wang, A. Proutiere, K. Ariu, Y. Jedra, A. Russo.
  23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. [proc.]
  
  

• Sample Complexity Lower Bounds for Linear System Identification
  Y. Jedra,  A. Proutiere.
  IEEE 58th Conference on Decision and Control (CDC), 2019. [doi] [arxiv]

Thesis

• Statistical Learning of Linearly Structured Systems: Identification, Control, and Reinforcement Learning.  
  PhD thesis, KTH Royal Institute of Technology, 2023. [thesis] [diva] (slides)