About me

I am an Assistant Professor in the Information Systems and Operations Management department at HEC Paris, and a Hi! Paris chair holder. My research focuses on data-driven decision making under parameter uncertainty, with applications in healthcare and algorithmic game theory. I received my Ph.D. in Operations Research from Columbia University in 2021 where my advisors were Prof. Vineet Goyal and Prof. Carri Chan. Before Columbia, I completed my master and undergraduate studies at Ecole polytechnique (France) in 2016, with a major in algorithms and optimization.

Info: Google Scholar / resume

Contact: grand-clement at hec dot fr

News:

Mar 25 - One new preprint on the separation between last-iterate, best-iterate, and random-iterate convergence properties for a broad family of learning dynamics for game-solving.

Jan 25 - One paper accepted at ICLR 2025, on the last-iterate convergence properties of regret-matching based algorithms in games.

Dec 24 - One paper accepted at AAAI 2025 as an oral presentation, on risk-aversion in sequential decision-making (joint with Marek Petrik and Xihong Su).

Nov 24 - One new preprint on the necessary and sufficient conditions for the tractability of robust Markov decision processes (joint with Nian Si and Shengbo Wang).

Publications and preprints

Journals:

• On the convex formulations of robust Markov decision processes
  Julien Grand-Clément, Marek Petrik.
  Mathematics of Operations Research (2024, forthcoming).
• The best decisions are not the best advice: Making adherence-aware recommendations
  Julien Grand-Clément, Jean Pauphilet.
  Management Science (2023, forthcoming). The code for the simulations is available here.
• Solving optimization problems with Blackwell approachability
  Julien Grand-Clément, Christian Kroer.
  Mathematics of Operations Research (2023), 49(2):697-728. Slides are available here.
• Robustness of Proactive Intensive Care Units Transfer Policies
  Julien Grand-Clément, Carri Chan, Vineet Goyal, Gabriel Escobar.
  Operations Research (2022) 71(5):1653-1688. The code for the simulations is available here.
• Quantifying Utilitarian Outcomes to Inform Triage Ethics: Simulated Performance of a Ventilator Triage Protocol Under SARS-CoV-2 Pandemic Surge Conditions
  Elizabeth Chuang, Julien Grand-Clément, Jen-Ting Chen, Carri Chan, Vineet Goyal, Michelle Ng Gong.
  American Journal of Bioethics – Empirical Bioethics (2022), vol. 13, no 3, p. 196-204.
• A First-Order Approach to Accelerated Value Iteration
  Vineet Goyal, Julien Grand-Clément.
  Operations Research (2022), 71(2):517-535.
• Robust Markov Decision Process: Beyond Rectangularity
  Vineet Goyal, Julien Grand-Clément.
  Mathematics of Operations Research (2022), 48(1):203-226.
• The Operator Approach to Entropy Games
  Marianne Akian, Stéphane Gaubert, Julien Grand-Clément, Jérémie Guillaud.
  Theory of Computing Systems (2019) 63(5), 1089-1130. A preliminary version appeared in STACS 2017.

Refereed conferences:

• Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
  Yang Cai, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng.
  (ICLR 2025)  International Conference on Learning Representations, 15th.
• Risk-averse Total-rewards MDPs with ERM and EVaR
  Xihong Su, Julien Grand-Clément, Marek Petrik.
  (AAAI 2025, oral) Proceedings of the AAAI Conference on Artificial Intelligence, 39th.
• Extensive-Form Game Solving Via Blackwell Approachability on Treeplexes
  Darshan Chakrabarti, Julien Grand-Clément, Christian Kroer.
  (NeurIPS 2024, spotlight) 38th Advances in Neural Information Processing Systems.
• Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
  Yang Cai, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng.
  (NeurIPS 2024) 38th Advances in Neural Information Processing Systems. Some slides and the code for the experiments.
• Regret Matching+: (In)Stability and Fast Convergence in Games
  Gabriele Farina, Christian Kroer, Julien Grand-Clément, Chung-Wei Lee, Haipeng Luo.
  (NeurIPS 2023, spotlight) 37th Advances in Neural Information Processing Systems. The code for the simulations is available here. Some slides are available here.
• Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
  Julien Grand-Clément, Marek Petrik.
  (NeurIPS 2023) 37th Advances in Neural Information Processing Systems.
• Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving
  Julien Grand-Clément, Christian Kroer.
  (NeurIPS 2021) Proceedings of the 34th Advances in Neural Information Processing Systems, 34:9587-9599 , 2021.
• First-Order Methods for Wasserstein Distributionally Robust MDP
  Julien Grand-Clément, Christian Kroer.
  (ICML 2021) Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2010-2019, 2021.
• Scalable First-Order Methods for Robust MDPs
  Julien Grand-Clément, Christian Kroer.
  (AAAI 2021) Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 12086-12094.

Working papers:

• Beyond discounted returns: Robust Markov decision processes with average and Blackwell optimality
  Julien Grand-Clément, Marek Petrik, Nicolas Vieille.
• Interpretable Machine Learning for Resource Allocation with Application to Ventilator Triage
  Julien Grand-Clément, You-Hui Goh, Carri Chan, Elizabeth Chuang, Vineet Goyal.
  Preliminary version accepted at the American Thoracic Society 2021 International Conference.
• Tractable Markov Decision Processes
  Julien Grand-Clément, Nian Si, Shengbo Wang.
• On the Separation Between Best-Iterate, Random-Iterate and Last-Iterate Convergence of Learning in Games
  Yang Cai, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng.

Technical report:

• From Convex Optimization to MDPs: A Review of First-Order, Second-Order and Quasi-Newton Methods for MDPs.

Teaching

• HEC Paris, 2021 - present:
  • Introduction to Data Science, graduate core course (~ 200 students)
  • Operations and Supply Chain Management, graduate core course (~ 300 students)
  • Sustainable Operations and Supply Chain Management, undergraduate core course (~ 140 students)
  • Sustainable Artificial Intelligence, undergraduate core course (~ 400 students)
  • Artificial Intelligence and Climate Change, certificate course (~ 50 students). Slides available here.

• Columbia University, 2016 - 2021, undergraduate & graduate courses (~ 450 students).
  • Convex Optimization (IEOR 6616).
  • Advanced Optimization (IEOR 4004).
  • Foundations of Optimization (IEOR 3608).
  • Dynamic Pricing & Revenue Management (IEOR 4601).
  • Game Theoretic Models of Operations (IEOR 4407).
  • Operations Management (IEOR 4000).