ATMOSPHERE was presented at the 32nd Conference on Neural Information Processing Systems, from 2nd to 8th December 2018, Monreal (Canada). The Thirty-second Annual Conference on Neural Information Processing Systems (NeurIPS) was a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

ATMOSPHERE project presented a paper about learning Granger causality matrices for multivariate point processes 

Flávio Figueiredo, from Federal University of Minas Gerais and member of the ATMOSPHERE project, presented a the paper entitled "Fast Estimation of Causal Interactions using World Processes".

In the paper, the authors focus on the task of learning Granger causality matrices for multivariate point processes. In order to accomplish this task, their work was the first to explorethe use of Wold processes. By doing so, the authors were able to develop asymptotically fast MCMC learning algorithms. With Nbeing the total number of events and K the number of processes, the learning algorithm has aO(N( log(N) + log(K)))costper iteration. This is much faster than theO(N3K2)orO(K3) for the state of theart. This approach, called GRANGER-BUSCA, is validated on nine datasets. This is an advance in relation to most prior efforts which focus mostly on subsets of the Memetracker data. Regarding accuracy, GRANGER-BUSCA is three times more accurate (in Precision@10) than the state of the art for the commonly explored subsets Memetracker. Due to GRANGER-BUSCA’s much lower training complexity,our approach is the only one able to train models for larger, full, sets of data.