8.2k citations
- Centre National de la Recherche ScientifiqueFR1.6k papers
- Sorbonne UniversitéFR1.2k papers
- Université Paris Sciences et LettresFR1k papers
- Laboratoire de Physique de l'Ecole Normale SupérieureFR820 papers
- Université Paris CitéFR738 papers
- Laboratoire Kastler BrosselFR357 papers
- Université Paris-SaclayFR322 papers
- Sorbonne Paris CitéFR275 papers
- Département de mathématiques et applicationsFR250 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR231 papers
- CEA Paris-SaclayFR196 papers
- Département d'InformatiqueFR189 papers
9 papers · 2 filters
Regression as Classification: Influence of Task Formulation on Neural Network Features
Lawrence Stewart, Francis Bach, Quentin Berthet +1
Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. However, practitioners often prefer to reformulate regressi…
On double-descent in uncertainty quantification in overparametrized models
Lucas Clarté, Bruno Loureiro, Florent Krzakala +1
Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estim…
Wavelet Score-Based Generative Modeling
Florentin Guth, Simon Coste, Valentin De Bortoli +1
Score-based generative models (SGMs) synthesize new data samples from Gaussian white noise by running a time-reversed Stochastic Differential Equation (SDE) whose drift coefficient…
Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems
Ashesh Chattopadhyay, Ebrahim Nabizadeh, Eviatar Bach +1
Data assimilation (DA) is a key component of many forecasting models in science and engineering. DA allows one to estimate better initial conditions using an imperfect dynamical mo…
Disentangling representations in Restricted Boltzmann Machines without adversaries
Jorge Fernandez-de-Cossio-Diaz, Simona Cocco, Remi Monasson
A goal of unsupervised machine learning is to build representations of complex high-dimensional data, with simple relations to their properties. Such disentangled representations m…
Do Residual Neural Networks discretize Neural Ordinary Differential Equations?
Michael E. Sander, Pierre Ablin, Gabriel Peyré
Neural Ordinary Differential Equations (Neural ODEs) are the continuous analog of Residual Neural Networks (ResNets). We investigate whether the discrete dynamics defined by a ResN…