Explore >> Select a destination

You are here

 djalil.chafai.net
A probabilistic proof of the Schoenberg theorem - Libres pensées d'un mathématicien ordinaire
| | windowsontheory.org
A blitz through classical statistical learning theory - Windows On Theory
7.3 parsecs away

Travel
| | Previous post: ML theory with bad drawings Next post: What do neural networks learn and when do they learn it, see also all seminar posts and course webpage. Lecture video (starts in slide 2 since I hit record button 30 seconds too late - sorry!) - slides (pdf) - slides (Powerpoint with ink and animation)...
| | fabricebaudoin.blog
Lecture 8. Sobolev inequalities on Dirichlet spaces: The Varopoulos approach | Research and Lecture notes
7.3 parsecs away

Travel
| | In this lecture, we studySobolev inequalities on Dirichlet spaces. The approach we develop is related to Hardy-Littlewood-Sobolev theory The link between the Hardy-Littlewood-Sobolev theory and heat kernel upper bounds is due to Varopoulos, but the proof I give below I learnt it from my colleague RodrigoBañuelos. It bypasses the Marcinkiewicz interpolation theorem,that was originally used...
| | fa.bianp.net
On the Convergence of the Unadjusted Langevin Algorithm
6.8 parsecs away

Travel
| | The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of some machine learning methods such as diffusion models and differentially private learning. In this post, I'll derive a simple convergence analysis of this method in the special case when the ...
| | marcobonzanini.com
PyData London 2018 - Marco Bonzanini
80.6 parsecs away

Travel
| Last weekend (April 27-29) we run PyData London 2018, the fifth edition of our annual conference (we also have a monthly meet-up, with currently 7,200+ members). The event is entirely run by volunteers, with the purpose of bringing the community together and raising money for NumFOCUS, the charity that provides financial support to open-source scientific...