About me

I am starting this Fall as a postdoctoral fellow at LIDS, MIT, working with Devavrat Shah, where I am generously supported by the Knut and Alice Wallenberg Foundation. My current research interest revolves around high dimensional sequential decision making with a particular interest in the fundamental limits of learning. Recently, I have been working on topics in reinforcement learning, multi-armed bandits, system identification and adaptive control, with the aim of understanding how to exploit structural assumptions (of practical relevance) to enable fast learning. 

I recieved my PhD from the EECS school at KTH Royal Institute of Technology, advised by Alexandre Proutiere, where I was also part of the WASP AI program. Prior to that, I received a M.Sc. degree in Applied and Computational Mathematics within the Engineering Physics' program at KTH. I received both my  B.Sc. degree and  M.Sc. degree in Mathematics and Computer Science from ENSIMAG, Grenoble, France, in 2015 and 2018, respectively.  

News

• [12/2023] Attending Neurips 2023! 

• [12/2023] Ingvar, Anastasios and Bruce are presenting our tutorial on Non-asymptotic Theory of SysID  at CDC2023

• [09/2023] Starting Fall 2023 I will be a Postdoctoral Fellow at LIDS, MIT working with Prof. Devavrat Shah.

• [09/2023] Our work on Entrywise Guarantees for Matrix Estimation in RL has been accepted to Neurips 2023

• [09/2023] Our work on discounted linear MDPs has been accepted at EWRL 2023

• [06/2023] Attending NORDSTAT 2023 where I presented our work on BlockMDPs

• [06/2023] I successfully defended my PhD thesis titled "Statistical Learning in Linearly Structured Systems: Identification, Control, and Reinforcement Learning". I am grateful for having Prof. Alexandre Rakhlin as my opponent,  and  Rs. Sci.  Alessandro Lazaric,   Ass. Prof. Sarah Dean,   and  Prof. Csaba Szepesvári as members of my thesis committee

• [04/2023] Attending AISTATS 2023 in Valencia to present our work on Block MDPs together with Junghyun Lee

• [03/2023] Presenting our work on Block MDPs at 2nd ASCAI workshop in TUM

• [12/2022] Presenting our work on regret minimization for LQR at the IEEE CDC 2022 full-day workshop on Statistical Learning Theory for Control

• [09/2022] Atteneding the Simons Institute Workshop on  Quantifying Uncertainty: Stochastic, Adversarial, and Beyond.