5 papers
Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift
Zhaobo Hu, Vincent Gauthier, Mehdi Naima
Distribution shift severely degrades the performance of deep forecasting models. While this issue is well-studied for individual time series, it remains a significant challenge in…
Modern Structure-Aware Simplicial Spatiotemporal Neural Network
Zhaobo Hu, Vincent Gauthier, Mehdi Naima
Spatiotemporal modeling has evolved beyond simple time series analysis to become fundamental in structural time series analysis. While current research extensively employs graph ne…
Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks
Zhaobo Hu, Vincent Gauthier, Mehdi Naima
Graph Neural Networks (GNNs) conventionally rely on standard Laplacian or adjacency matrices for structural message passing. In this work, we substitute the traditional Laplacian w…
The ascent lattice on Dyck paths
Jean-Luc Baril, Mireille Bousquet-Mélou, Sergey Kirgizov +1
In the Stanley lattice defined on Dyck paths of size , cover relations are obtained by replacing a valley by a peak . We investigate a greedy version of this lattice, f…
A lattice on Dyck paths close to the Tamari lattice
Jean-Luc Baril, Sergey Kirgizov, Mehdi Naima
We introduce a new poset structure on Dyck paths where the covering relation is a particular case of the relation inducing the Tamari lattice. We prove that the transitive closure…