📢 I am on the job market and planning to defend my PhD thesis in Fall 2025 — feel free to reach out !
I am Nikita Lagrange, a PhD student at Institut Curie in Paris under the supervision of Dr. Hervé Isambert and the co-supervision of Dr. Barbara Bravi.
My thesis focuses on the development of a new search-and-score algorithm for causal discovery in the presence of latent variables using information theory.
PhD in Computer Science
Sorbonne University
M.Sc. in Bioinformatics & Modelling
Sorbonne University
B.Sc. in Life Sciences
Sorbonne University
I am a PhD student at Institut Curie in Paris. My thesis focuses on causal discovery. More specifically, I am working on extending the MIIC algorithm, developed within the Isambert Lab to a search-and-score mode.
The goal is to improve the efficiency and robustness of causal discovery algorithms, particularly when applied to complex and non-linear biomedical data.
Beyond that, I am interested in developing machine learning algorithms that are more grounded in human reasoning and are interpretable.
Presentation of my thesis work at the retreat for young researchers from Institut Curie, Centre des Cordeliers, and Institute of Biotechnology of the Czech Academy of Sciences in Prague, Czech Republic
Sep 22, 2024
Presentation of my thesis project and preliminary results to the AI-DSCY team
Sep 27, 2023
Representative of doctoral students on the EDITE doctoral school board
Participation in the board and involvement in key decision-making processes.
Reviewer for the NeurIPS BDU Workshop 2024
Our method for search-and-score learning of ancestral graphs has been accepted at ICML 2025 in Vancouver 🇨🇦 ! Looking forward to presenting this work 🎉 !
I presented my PhD thesis in 3 minutes during the EDITE 2025 Doctoral Day at the Centre Pompidou in Paris 🇫🇷 . An exciting challenge in science communication 📣 !
📧 nikita.lagrange@curie.fr or nikita.lagrange@tutanota.com
📍Institut Curie, Research Center, CNRS-UMR168
Pavillon Curie, 1st floor, Office 01.09.b
11, rue Pierre et Marie Curie
75005 Paris