Portrait

Alexandre Proutiere

Professor at the Decision and Control Systems division in the EECS school at KTH, Royal Institute of Technology.
Research interests: Machine Learning and AI, reinforcement learning, unspervised learning, statistics, stochastic processes, control; Applications to communication and social networks, cybersecurity.
Short bio: Researcher at Microsoft Research (Cambridge) from 2007 to 2011, Research Engineer at France Telecom R&D from 2000 to 2006, Invited lecturer and researcher at the computer science department ENS Paris from 2004 to 2006. Education: PhD in Applied Mathematics from Ecole Polytechnique, Graduated in Mathematics from Ecole Normale Superieure (Paris), Engineering degree from Telecom Paris, Engineer from Corps des Mines.

News

March 28, 2025 -- Welcome to the PhD defense of Simon Lindståhl, room D3 at 10AM.

January, 2025 -- Together with Aris Gionis, Danica Kragic, Kalle Johansson, Jana Tumova, I lead a strategic initiative 'KTH Center for AI', to coordinate AI research at KTH.

November, 2024 -- Keynote at DDQC (Data-Driven Queueing Challenges) III at EURANDOM, Eindhoven.

July, 2024 -- I had the priviledge to chair and organize Stochastic Networks conference at KTH. See also historical data on the conference here.

Selected recent publications

Deming Yuan, Alexandre Proutière, Guodong Shi. "Multi-agent Online Optimization". Found. Trends Optim. 7(2-3): 81-263 (2024) Book published by Now Publishers

Stefan Stojanovic, Yassir Jedra, Alexandre Proutière. "Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation". NeurIPS 2024

Frédéric Zheng, Alexandre Proutière. "Conformal Predictions under Markovian Data". ICML 2024

Po-An Wang, Kaito Ariu, Alexandre Proutière. "On Universally Optimal Algorithms for A/B Testing". ICML 2024

Yassir Jedra, William Réveillard, Stefan Stojanovic, Alexandre Proutière. "Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery". ICML 2024

Yassir Jedra, Alexandre Proutière. "Finite-Time Identification of Linear Systems: Fundamental Limits and Optimal Algorithms". IEEE Trans. Autom. Control. 68(5): 2805-2820 (2023)

Yassir Jedra, Junghyun Lee, Alexandre Proutière, Se-Young Yun. "Nearly Optimal Latent State Decoding in Block MDPs". AISTATS 2023

Filippo Vannella, Alexandre Proutière, Jaeseong Jeong. "Best Arm Identification in Multi-Agent Multi-Armed Bandits". ICML 2023

Alessio Russo, Alexandre Proutière. "Model-Free Active Exploration in Reinforcement Learning". NeurIPS 2023

Stefan Stojanovic, Yassir Jedra, Alexandre Proutière. "Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning". NeurIPS 2023

Ruo-Chun Tzeng, Po-An Wang, Alexandre Proutière, Chi-Jen Lu. "Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits". NeurIPS 2023

Filippo Vannella, Alexandre Proutière, Jaeseong Jeong. "Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits". NeurIPS 2023

Po-An Wang, Ruo-Chun Tzeng, Alexandre Proutière. "Best Arm Identification with Fixed Budget: A Large Deviation Perspective". NeurIPS 2023