Those are mostly blog posts, notes, talk slides, nice pictures and various things about mathematics, statistics, CS and machine learning.
- Super-Catalan (Janvier 2022)
- Une question non-résolue, vieille de 150 ans, et probablement très inutile.
- The ConvMixer architecture: 🤷 (December 2021)
- I am training a deep network on a GPU using the Flux.jl library. There are two takeaway messages: 1) patches are all you need, 2) in Julia, the ConvMixer *largely* fits in one Tweet.
- Diffusion models (March 2023)
- A small mathematical summary.
- The Kullback-Leibler divergence between Gaussians (June 2022)
- I'll know once and for all where to find this damn formula.
- The double descent phenomenon (November 2021)
- Why do overparametrized networks do well?
- An inverse visualization for the elliptic law (March 2021)
- A beautiful colorplot of the characteristic polynomial of random matrices.
- Gradient descent over convex landscapes (April 2022)
- A note on the most elementary result of convex optimization: the speed of convergence is determined by the conditionning number of the Hessian.
- The dimension of invariant and equivariant linear layers (July 2021)
- We compute the dimension of equivariant linear layers in neural architectures.
- The Jarzynski estimator (March 2022)
- An elegant estimator for free energies.
- The Kelly criterion, crypto exchange drama, and your own utility function (November 2022)
- The most misused and simplistic investment criterion.
- The point of view of Professor Parapine (November 2022)
- An interesting vision of science from one century ago.
- Waves on donuts (August 2021)
- A nice plot of random Laplace eigenfuctions on the torus, also called random arithmetic waves.
- Random line processes (August 2021)
- How to draw random lines on the plane.
- Random analytic functions: Ryll-Nardzewski's theorem (April 2021)
- What happens at the boundary of the disk of convergence of random analytic series.
- Robbins' version of the Stirling approximation (November 2022)
- A handy, easy-to-remember estimate for the error in Stirling's approximation.
- Slides (February 2021)
- Html slides of some of my talks
- Tips and tricks in Julia (2022)
- A personnal collection of Julia's nice tricks.