1.6k citations
- Université Gustave EiffelFR149 papers
- Centre National de la Recherche ScientifiqueFR64 papers
- Institutt for Grafiske MedierNO25 papers
- Université Paris CitéFR14 papers
- École nationale des ponts et chausséesFR10 papers
- Institut de Recherche en Informatique FondamentaleFR10 papers
- IFP Énergies nouvellesFR8 papers
- UniLaSalle Amiens (ESIEE-Amiens)FR8 papers
- Université Paris-SaclayFR8 papers
- Hankuk University of Foreign StudiesKR6 papers
- Laboratoire d'Informatique, du Traitement de l'Information et des SystèmesFR6 papers
- Paris-Est SupFR6 papers
12 papers · 1 filter
Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention
Léo Hein, Giovanni de Nunzio, Giovanni Chierchia +2
Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While f…
Sliced ReLU attention: Quasi-linear contextual expressivity via sorting
François-Xavier Vialard, Siwan Boufadène
We introduce sliced ReLU attention, a new attention mechanism that departs structurally from both softmax and its approximation alternatives. Instead of applying a nonlinearity to…
Data Science: a Natural Ecosystem
Emilio Porcu, Roy El Moukari, Laurent Najman +2
This manuscript provides a systemic and data-centric view of what we term essential data science, as a natural ecosystem with challenges and missions stemming from the fusion of da…
Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
Raphaël Barboni, Gabriel Peyré, François-Xavier Vialard
We study the convergence of gradient methods for the training of mean-field single-hidden-layer neural networks with square loss. For this high-dimensional and non-convex optimizat…
The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks
Sholom Schechtman, Nicolas Schreuder
We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large clas…
SWMLP: Shared Weight Multilayer Perceptron for Car Trajectory Speed Prediction using Road Topographical Features
Sarah Almeida Carneiro, Giovanni Chierchia, Jean Charléty +2
Although traffic is one of the massively collected data, it is often only available for specific regions. One concern is that, although there are studies that give good results for…