6 citations
- École Normale Supérieure - PSLFR2 papers
- CERMICSFR1 paper
- Département d'InformatiqueFR1 paper
- École Centrale de LyonFR1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Freie Universität BerlinDE1 paper
- Imperial College LondonGB1 paper
- Institut Camille JordanFR1 paper
- Institut national de recherche en sciences et technologies du numériqueFR1 paper
- Institut Universitaire de FranceFR1 paper
- Laboratoire d’Analyse et de Mathématiques AppliquéesFR1 paper
- Laboratoire d'Informatique Gaspard-MongeFR1 paper
7 papers
Energy decomposition by potential level
Nicolas Bouleau
In the first part we study excessive functions for a Markov process that are continuous semimartingales along the sample paths. The property then follows from the theory of local t…
PyTorchFire: A GPU-Accelerated Wildfire Simulator with Differentiable Cellular Automata
Zeyu Xia, Sibo Cheng
Accurate and rapid prediction of wildfire trends is crucial for effective management and mitigation. However, the stochastic nature of fire propagation poses significant challenges…
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
Pierre-Cyril Aubin-Frankowski, Yohann De Castro, Axel Parmentier +1
Many real-world decision problems require solving, again and again, combinatorial optimization instances drawn from a common distribution. A recent line of structured learning meth…
Generalize cross-ratios in n-dimensional Plane-Based Geometric Algebra
Enzo Harquin, Stephane Breuils, Pascal Monasse +2
We develop a complete theory of projective cross-ratios in n-dimensional Plane-Based Geometric Algebra (PGA), R(n,0,1), covering geometric objects of every grade: finite and ideal…
A Fully Discrete Nonnegativity-Preserving FEM for a Stochastic Heat Equation
Owen Hearder, Claude Le Bris, Ana Djurdjevac
We consider a stochastic heat equation with nonlinear finite-rank space-coloured multiplicative noise that admits a unique nonnegative solution when given nonnegative initial data.…
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its su…