Notes

Those are mostly blog posts, notes, talk slides, nice pictures and various things about mathematics, statistics, CS and machine learning.

Flow-based generative models

These series of notes focus on diffusion-based generative models, like the celebrated Denoising Diffusion Probabilistic Models; they contain the material I regularly present as lectures in some working groups for mathematicians or math graduate students, so the style is tailored for this audience. In particular, everything is fitted into the continuous-time framework (which is not exactly how it is done in practice).

In 2025 S2, I will probably completely rewrite and reorder these notes. I think that nowadays, there is no reason other than historic to present diffusion models by starting from the reversal of the SDE. The Flow Matching perspective should definitely be favored, the rest should only be anecdotic.

Deep learning

Gradient descent

Probability and maths

Heavy tails

The Gaussian world

Nice pictures

Misc