Emmarius Delar

PhD Student in Reinforcement Learning • PSL Research University (Paris Dauphine)

Research Interests

Machine Learning • Monte Carlo Tree Search • Combinatorial Optimization • Federated Learning • Gene Regulatory Networks • Intelligent Mesh Generation • Economics & Game Theory

Education

PhD in Reinforcement Learning

PSL Research University (Paris Dauphine)

Nov. 2025 - present

Advised by Prof. Tristan Cazenave.

MSc Artificial Intelligence, Systems, Data

PSL Research University (Dauphine, ENS Ulm, Mines Paris)

Sept. 2024 - Sept. 2025

Highly selective program with strong theoretical and practical foundations in AI, covering Learning Theory, Optimization, Inverse Problems, Kernel Methods, and Mathematics of Deep Learning.

MS1 Applied Mathematics and Statistics

University of Rennes

Sept. 2023 - May 2024

GPA: 3.7/4 (with high honours • rank 2)

Magistère Statistics and Economics Modelling

University of Rennes

Sept. 2023 - May 2024

Highly selective program in advanced statistical and economic modeling. GPA: 3.7/4 (with high honours)

BSc Mathematics and Computer Science

University of Rennes

Sept. 2020 - Apr. 2023

Minor in Economics

Research Experience

AI Research Intern

LAMSADE, Paris & Orange Labs, Châtillon

Apr. 2025 - Sept. 2025

Contributing to the TREES project (TowaRds Energy Efficient diStributed learning for 6G), led by Orange and supervised by Tristan Cazenave, Morgan Chopin, and Nancy Perrot.

Conducting research on Monte Carlo Tree algorithms to develop efficient methods for optimizing network topologies in Federated Learning environments.

Federated Learning MCTS Graph Optimization 6G Networks Energy Efficiency

AI Research Intern

CERFACS, Toulouse

May 2024 - Aug. 2024

Continued research on uncertainty reduction for atmospheric dispersion models, supervised by Eliott Lumet and Mélanie Rochoux.

Implemented dimensionality reduction techniques using Machine Learning and Deep Learning for statistical emulation of atmospheric dispersion models.

Computational Fluid Dynamics Machine Learning Transfer Learning Autoencoders

Selected Projects

Non-convex Inverse Problems

Matrix reconstruction using Sparse PCA with convex and non-convex approaches

Mar. 2025

Kernel Methods for DNA

Implemented SVM and Kernel Logistic Regression for DNA sequence classification

Mar. 2025

L-BFGS Optimization

Advanced optimization techniques for large-scale machine learning problems

Jan. 2025

GAN Improvements

Implemented rejection sampling methods and Optimal Budget RS for GANs

Nov. 2025

Honors & Awards

ENS Challenge Data - 1st Place

InsurPrime Challenge, Crédit Agricole

Ranked 1st out of 89 participants. Applied scientific approaches to solve real-world insurance problems. Final grade: 4.0/4.0

March 2025

Skills

Programming Languages

Python Julia R SAS SQL LaTeX

ML & Data Science

NumPy Scikit-learn cvxopt cvxpy

Tools & Technologies

Git Docker Linux Bash

Languages

French (Native) English (C1)
Download Full CV (PDF)