Moïse Blanchard

Email: moiseb (at) mit (dot) edu
Linkedin profile, Google scholar

I am a fifth-year PhD student in the Operations Research Center and Laboratory for Information and Decision Systems at MIT, where I am advised by Prof. Patrick Jaillet. My research interests lie at the intersection of learnability in machine learning and statistics, online algorithms and optimization in decision-making. Prior to my PhD, I graduated as the valedictorian of Ecole Polytechnique in 2019 with a M.S. degree in Applied Mathematics, and a B.S. degree in Mathematics, Computer Science and Physics. During my PhD and my undergraduate studies, I had the pleasure to work with Prof. Steve Hanneke, Prof. Alexandre Jacquillat, Prof. Jesús De Loera, Prof. Laurent Massoulié and Prof. Gabriel Peyré. Here is my Curriculum Vitae (CV).

Universal Regression with Adversarial Responses
Moïse Blanchard and Patrick Jaillet
Annals of Statistics, 51 (3), 2023
Fréchet Mean Set Estimation in the Haussdorff Metric, via Relaxation
Moïse Blanchard and Adam Jaffe
Bernoulli, 2023
Probabilistic bounds on the k-Traveling Repairman Problem and the k-Traveling Salesman Problem
Moïse Blanchard, Alexandre Jacquillat, and Patrick Jaillet
Mathematics of Operations Research, 2021 Additional Results and Extensions
On the length of monotone paths in polyhedra
Moïse Blanchard, Jesús A. De Loera, and Quentin Louveaux
SIAM Journal on Discrete Mathematics 35 (3), 2021

Tight Bounds for Local Glivenko-Cantelli
Moïse Blanchard and Václav Voráček
35th International Conference on Algorithmic Learning Theory (ALT), 2024
Memory-Constrained Algorithms for Convex Optimization via Recursive Cutting-Planes
Moïse Blanchard, Junhui Zhang, and Patrick Jaillet
37th Neural Information Processing Systems (NeurIPS), 2023
Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal
Moïse Blanchard, Junhui Zhang, and Patrick Jaillet
36th Annual Conference on Learning Theory (COLT), 2023
Universal Online Learning: an Optimistically Universal Learning Rule
Moïse Blanchard
35th Annual Conference on Learning Theory (COLT), 2022
Universal Online Learning with Bounded Loss: Reduction to Binary Classification
Moïse Blanchard and Romain Cosson
35th Annual Conference on Learning Theory (COLT), 2021
Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions
Moïse Blanchard and Amine Bennouna
10th International Conference on Learning Representations (ICLR), 2022
Universal Online Learning with Unbounded Losses: Memory Is All You Need
Moïse Blanchard, Romain Cosson, and Steve Hanneke
33rd International Conference on Algorithmic Learning Theory (ALT), 2022

MIT 6.215/15.093J | Optimization Methods, Fall 2021
Teaching Assistant
MIT 15.072 | Advanced Analytics Edge, Fall 2020
Teaching Assistant
Classes Préparatoires, Mathematics, 2017-2019
Instructor in mathematics for French undergraduate students

''Contextual bandits and universal learning'', TB07. Artificial Intelligence in Operations, INFORMS Annual Meeting, 2023
''Probabilistic bounds on the k-TSP and TRP'', MD39. Transportation Science and Logistics Student Paper Prize, INFORMS Annual Meeting, 2023
''Contextual bandits and universal learning'', Cornell Young Researcher Workshop, 2023
''Memory-constrained convex optimization: is cutting-planes optimal?'', Invited talk at TTIC (Toyota Technological Institute at Chicago), 2023
''Quadratic memory is necessary for optimal query complexity in convex optimization: Center-of-mass is Pareto-optimal'', COLT 2023
''Universal Regression with Adversarial Responses'', INFORMS Annual Meeting 2022
''Learnability in universal online learning and adversarial regression'', Invited talk at Université Pierre et Marie Curie, Laboratoire Jacques-Louis Lions GTT, 2022
''Universal Online Learning: an Optimistically Universal Learning Rule'', COLT 2022 (Video)
''Reduction from Binary Classification for Universal Online Learning'', COLT 2022 (Video)
''Universal Online Learning with Unbounded Loss: Memory is All you Need'', ALT 2022
''Learnability in Online Learning'', MIT LIDS Conference, 2022
''The Representation Power of Neural Networks'', MIT SIAM Seminar 2021 (Video)
''Online Matchings on Unknown Bipartite Graphs'', INFORMS Annual Meeting 2020

Winner of the INFORMS Transportation Science & Logistics (TSL) best student paper award, 2023
Air Force Office of Scientific Research Grant (AFOSR), with Prof. Patrick Jaillet, 2023
COLT 2022 Best student paper runner-up, 2022
Paper: Universal online learning: an Optimistically universal learning rule
Best Presentation at LIDS Student Conference, MIT, 2022
Paper: Universal Regression with Adversarial Responses (with Prof. Patrick Jaillet)
Bronze medal, Alibaba Global Mathematics Competition, 2022
Honorable Mention, Alibaba Global Mathematics Competition, 2021
2nd Prize, The East Coast Data Open by Citadel, 2020
Laplace medal, French Science Academia, 2019
Distinction as Valedictorian of Ecole Polytechnique
Rivot medal, French Science Academia, 2019
Best student research for the paper: On the length of monotone paths in polyhedra (with Prof. Jesus De Loera and Prof. Quentin Louveaux)
Bronze Medal, 46th International Physics Olympiad (IPhO), 2015
Bronze Medal, 55th International Mathematics Olympiad (IMO), 2014
Silver Medal, 18th Junior Balkan Mathematics Olympiad (JBMO), 2014
1st Prize, Concours Général in Mathematics, 2014