Here are thes slides of my presentation at the International Symposium on Forecasting today:

I discussed probabilistic Forecasting with quasi-randomized networks, sequential split conformal prediction, and GPU computation in Python package nnetsauce (thanks to JAX). Bonus slides: Automated Forecasting (sort of) with nnetsauce’s LazyMTS and time series cross-validation with nnetsauce’s TimeSeriesSplit.

Thanks to the organizers for allowing me to present my independent work on nnetsauce. These conferences are always a great opportunity to meet new people (or people we’ve heard about for a long time), and share our passion.