Education

• M.S. MVA ENS Paris-Saclay for research in applied mathematics and AI, Paris-Saclay University, 2024 (expected)
  Currently 17.7/20 (GPA : 4.0/4.0)

  • Semester 1 :
    Convex optimization and applications in machine learning (by A. D’ASPREMONT)
    Object recognition and computer vision (by G. VAROL, I. LAPTEV, J. PONCE, C. SCHMID, J. SIVIC, M. AUBRY)
    Advanced learning for text and graph data ALTEGRAD (by M. VAZIRGIANNIS)
    Geometric data analysis (by J. FEYDY)
    Time series learning (by L. OUDRE)
    Introduction to Probabilistic Graphical Models and Deep Generative Models (by P. LATOUCHE, P.A. MATTEI)
    Deep learning and signal processing, introduction and industrial applications (by T. COURTAT)

  • Semester 2 :
    Apprentissage et génération par échantillonnage de probabilités (by S. MALLAT)
    Generative models for images (by B. GALERNE, A. LECLAIRE)
    Deep learning for medical imaging (by. O. COLLIOT, M. VAKALOPOULOU)
    Deep Learning in Practice (by G. CHARPIAT)
    Reinforcement Learning (by E. Rachelson, E. Kaufmann)
    Graph in Machine Learning (by Google DeepMind)

• M.S. in Applied Mathematics, INSA Rennes engineering school, 2023
  GPA : 4.0/4.0 (valedictorian)

  • 2022 - 2023 :
    Uncertainty and sensitivity analysis in engineering
    Optimization under uncertainty
    Reliability and Survival Analysis
    Sparsity in Signal and Image Processing
    Rare Events Estimation and Simulation

  • 2021 - 2022 :
    Markov chain (discrete and continuous) and Martingale
    Operational Research (PLNE, Simplex, Branch and Bound)
    Risk and Scoring (Generalized Regression)
    Time series
    C++
    Introduction to finite differences

  • 2020 - 2021 :
    Inferential Statistics, Linear Regression Models, Data Analysis - PCA, CFA, MCA (R)
    Differential Equation Modelling (Matlab)
    Continuous Optimization (Matlab), Discrete Optimization
    Markovian Models (R, Python)
    Numerical Methods of Linear, Non-Linear (Python/Matlab)
    C language

CV

Work experience

• Apr. - Oct. 2024: ML Research intern at (Team Valeo.ai)
  Supervisor: Spyros Gidaris, Florent BARTOCCIONI
  Subject: “Tokenization from multi-camera autonomous drivin data”
  Outcomes: (Ongoing)

• Feb. - Aug. 2023: ML Research intern at
  Supervisor: Alexandre Mayerowitz
  Subject: “Building segmentation and polygonalization from very high resolution satellite imagery”
  Outcomes: Creation of a new architecture based on HRNet and Attraction field Map representation which enabled us to obtain better segmentation masks, respecting the coherence constraints: segment sharing for terraced houses, polygon complexity, accuracy: 1 pixel and robustness: must work on all types of landscape.*

• July. - Sept. 2022: ML Research intern at
  Supervisor: Julien Keutchayan
  Subject: “Insider threat detection within companies using temporal graphs”
  Outcomes: Creation of a new architecture to detect malicious activity in a company. Malicious activity can be characterised as much by a one-off action as by a series of incoherent actions. It also depends on the person’s role within the company. The solution was to create a temporal graph of activities for each employee and then, at a higher level, to introduce a graph activity for the company. Malicious activity is then detected in a self-supervised manner using an auto-encoder with graph activity embeddings.

• Feb. - May 2021: Research assistant at (Lab. M2S at ENS Rennes)
  Collaborator: Jack Prioux, Fabien Renouf
  Subject: “Workload planning for a professional women’s handball team based on data from various sensors”
  Outcomes: Statistics and data visualization.

• July. - Aug. 2021: ML intern at
  Supervisor: Jordan Tremoureux
  Subject: “Predicting the cost of a YouTube influencer sponsorship based on key performance indicators”
  Outcomes: Data manipulation in SQL tables or Mongo databases, followed by data cleaning, visualisation and spline regression finetuning to obtain an explainable model.

Skills

• Programming
  Python, R, MATLAB, Julia, C, C++
• Data Bases
  Neo4j, SQL, MongoDB
• Machine Learning
  Pytorch, TensorFLow, Pandas, Numpy, Sklearn, Statsmodels
• Visualization
  Wandb, TensorBoard, Plotly, Dash, Matplotlib, Seaborn
• Typing
  Latex, Markdown
• Cloud
  GCP
• Other
  Docker, Git, GitHub

Hobbies

• Handball
  National level player (under 18 y.o.)
  Uni. team coach
  Uni. French Championship (2017 and 2020)
• Hiking / Treking
  GR20 (Corsica) : 10 days, 180km, 13.000 D+
  GR10 (Pyrennees) : 4 days