Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
An Alternative to the Log-Likelihood with Entropic Optimal Transport
Published:
This paper explores the entropic optimal transport (EOT) loss and its estimator in parameter estimation, comparing its advantages over traditional likelihood methods, such as improved robustness, faster convergence, and resilience to bad local optima, with a focus on theoretical justification and experimental validation in Gaussian Mixture Models.
Discrete Morse Theory for Relative Cosheaf Homology
Published:
This paper aims to generalize discrete Morse theory in the context of relative cosheaf homology on filtrations of finite simplicial complexes, enabling faster computations. These methods are extended to persistent cosheaf homology for longer filtrations.
Robustness in Neural ODEs and SDEs
Published:
Recent studies show that Neural ODEs are more robust against adversarial attacks than traditional DNNs, but as complexity increases, concerns about robustness and expressivity arise, prompting exploration of stochastic noise regularization.
Spectral Methods for Clustering in Finance
Published:
This report gathers tools from spectral graph theory to analyze stock market relation graphs, focusing on spectral embedding for positioning companies in Euclidean space and exploring graph entropy to classify graphs and detect regime changes, with a generalization to directed weighted graphs and in-depth explanations of the underlying concepts and algorithms.
Pixel Art
Published:
Small project using C++ and SFML to depixelize pixel art.
Forest Classification - Kaggle Challenge
Published:
This Kaggle challenge involved a classification problem (with 7 different classes) based on a dataset of forest parcels. The data consisted of 55 columns, including 11 numerical variables and 2 categorical variables (with 4 and 40 classes, respectively). To tackle this problem, we employed strategies detailed chronologically in this report. After an initial data exploration phase and attempts at dimensionality reduction, we tested several classic algorithms and proceeded with optimizations where possible.
3D Graphics with OpenGL
Published:
Small project using the OpenGL library to draw a complex 3D scene.
Elliptic Curve Cryptography
Published:
Mini project studying elliptic curves on finite field, from basic properties to Hasse theorem and Schoof’s algorithm. Accompanying C++ library with GMP implementing these results.
mini_projects
Denoising Levy Probabilistic Models (DLPM)
Published:
This paper introduces a novel framework to use heavy-tailed noise in the denoising diffusion paradigm, which constitutes a generalization of the original DDPM method. Using heavy-tailed noise is shown to bring benefits in various contexts: heavy-tailed data distributions, better robustness to class imbalance, and smaller computational time.
Piecewise deterministic generative models
Published:
We introduce a novel class of generative models based on piecewise deterministic Markov processes (PDMPs), which combine deterministic motion with random jumps. Like diffusions, PDMPs can be reversed in time. We derive explicit expressions for jump rates and kernels in the time-reversed processes and propose efficient training methods and approximate simulation techniques. Additionally, we provide bounds on the total variation distance between the data and model distributions, supported by promising numerical simulations.
news
MAA106 Teaching
Published:
Finished TA’ing MAA106 numerical analysis course in Ecole Polytechnique. Thanks Maxime Breden for the teaching experience and congrats to the students!
Diffusion Models Summer School
Published:
Attending the Alan Turing Institute Summer School on Diffusion Models in London.
PDMP Accepted to NeurIPS
Published:
Our generative PDMP project is accepted to NeurIPS 2024!
PDMP on the Road
Published:
Presenting PDMP at both NeurIPS in Paris and official NeurIPS in Vancouver.
DLPM Accepted to ICLR
Published:
Heavy-tailed diffusion with DLPM accepted at ICLR 2025!
DLPM Talk at Polytechnique
Published:
Presenting DLPM at Ecole Polytechnique.
Diffusion Reading Group Launch
Published:
Launching the diffusion model reading group in Inria Paris. Feel free to reach out if you want to join!
DMPM Talk at Polytechnique
Published:
Presenting our discrete diffusion DMPM project at Ecole Polytechnique.
Oberwolfach Workshop
Published:
Attending the mini-workshop ‘Statistical Challenges for Deep Generative Models’ in legendary Oberwolfach, Germany.
Visit to Padova
Published:
Invited in Padova by Giovanni Conforti to explore cosmological applications of diffusion models. Looking forward to working with such a great person!
DLPM at ICLR 2025
Published:
Presenting DLPM at ICLR 2025.
DMPM Accepted to ICML
Published:
Our discrete diffusion project DMPM is accepted in ICML 2025!
Sakana AI Internship
Published:
I am starting an internship at Sakana AI in Tokyo, advised by legendary Stefano Peluchetti (who discovered flow matching a year before… flow matching).
Sakana Research Retreat
Published:
I am co-organising a 5-day research retreat with Sakana’s research staff!
Algorithm and Data Dependent Generalization Bounds for Score-Based Generative Modeling accepted to NeurIPS
Published:
Our work on algorithm and data dependent generalization bounds for diffusion models is accepted to NeurIPS 2025!
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Piecewise Deterministic Generative Models
Published in NeurIPS 2024, 2024
We introduce a novel class of generative models based on piecewise deterministic Markov processes (PDMPs), which combine deterministic motion with random jumps. Like diffusions, PDMPs can be reversed in time. We derive explicit expressions for jump rates and kernels in the time-reversed processes and propose efficient training methods and approximate simulation techniques. Additionally, we provide bounds on the total variation distance between the data and model distributions, supported by promising numerical simulations.
Denoising Levy Probabilistic Models (DLPM)
Published in ICLR 2025, 2025
This paper introduces a novel framework to use heavy-tailed noise in the denoising diffusion paradigm, which constitutes a generalization of the original DDPM method. Using heavy-tailed noise is shown to bring benefits in various contexts: heavy-tailed data distributions, better robustness to class imbalance, and smaller computational time.
Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptions
Published in ICML 2025, 2025
This paper introduces a novel framework for discrete data generation on the hypercube ${0, 1}^d$. We establish theoretical and methodological alignment with classical continuous score-based modesls. We demonstrate the effectiveness of this approach on low and high dimensional datasets (Binary MNIST), beating other state-of-the-art methods like Discrete Flow Matching
Algorithm and Data Dependent Generalization Bounds for Score-Based Generative Models
Published in NeurIPS 2025, 2025
This paper studies the generalization property of diffusion models through the lens of statistical learning. We develop a perspective that enables using existing tools to characterize the generalization ability of these generative models.
talks
Denoising Levy Probabilistic Model (DLPM)
Published:
Denoising Levy Probabilistic Model (DLPM)
Published:
Denoising Markov Probabilistic Model (DMPM)
Published:
Denoising Levy Probabilistic Model (DLPM)
Published:
teaching
Master X-HEC Data Science and AI for Business/Finance
Admission procedure, Ecole Polytechnique - HEC, 2024
Assisting the admission team during the multiple rounds of the selection process by conducting the mathematical interviews.
Numerical Analysis MAA106
Undergraduate course, Ecole Polytechnique, CMAP, 2024
TA’d a 4 months course for 1st year students on numerical analysis.
Master X-HEC Data Science and AI for Business/Finance
Admission procedure, Ecole Polytechnique - HEC, 2025
Assisting the admission team during the multiple rounds of the selection process by conducting the mathematical interviews.