Implementing NMF with a PAC-Bayesian approach relying upon block gradient descent

UCL ELLIS Unit

An AI Hedge Fund Team

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Kinda awesome beamer theme

Code associated with the article: Federated Learning with generalisation guarantees.

Simple Python scripts to clean up and flatten ArXiv LaTeX submissions.

Website of FERN-UK

Matériel rédigé pour un cours/td de 30h d'introduction aux réseaux de neurones à l'intention élèves de Master 2 en statistiques (automne 2019, Université de Lille, Département de Mathématiques).

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Materials for my scikit-learn tutorial

Clustering and Predictions with Multi-Task Gaussian Processes

Code for paper: On Margins and Derandomisation in PAC-Bayes

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Probabilistic reasoning and statistical analysis in TensorFlow

Virtual Seminar Series on Bayesian Decision-making and Uncertainty

Code for pre-print "Measuring dissimilarity with diffeomorphism invariance" (2022)

Code from my internship at University College of London, supervised by Benjamin Guedj and Antoine Vendeville on the analysis of opinion dynamics on social networks.

Code for reproducible experiments presented in KSD Aggregated Goodness-of-fit Test. https://arxiv.org/abs/2202.00824 NeurIPS 2022

Documentation for GitHub Copilot

Reproducibility code for MMD Aggregated Two-Sample Test, by Schrab, Kim, Albert, Laurent, Guedj and Gretton: https://arxiv.org/abs/2110.15073

biblatex is a sophisticated bibliography system for LaTeX users. It has considerably more features than traditional bibtex and supports UTF-8

Machine learning in Python with scikit-learn MOOC