Collection 2022 - T3 - WS1 - Non-Linear and High Dimensional Inference

In statistical learning and modern statistics, it is usually assumed that although data is observed in very high dimension, it actually live on — or near — a geometric structure of low dimension. The knowledge of such a low-complexity structure is of fundamental importance to improve both theoretical and computational aspects of a learning procedures.

Appears in collection : 2022 - T3 - Geometry and statistics in data sciences

Organizer(s) Aamari, Eddie ; Aaron, Catherine ; Chazal, Frédéric ; Fischer, Aurélie ; Hoffmann, Marc ; Le Brigant, Alice ; Levrard, Clément ; Michel, Bertrand
Date(s) 10/3/22 - 10/7/22
linked URL https://indico.math.cnrs.fr/event/7545/

All the collection videos (16)

published on October 3, 2022

Scaling ResNets in the Large-depth Regime

By Adeline Fermanian

published on October 3, 2022

Overcoming the curse of dimensionality with deep neural networks

By Sophie Langer

published on October 4, 2022

Learning on and near Low-Dimensional Subsets of the Wasserstein Manifold

By Alex Cloninger

published on October 4, 2022

Extrinsic and Intrinsic Operator Estimations for Manifold Learning

By John Harlim

published on October 4, 2022

A graph coupling view of dimension reduction

By Franck Picard

published on October 4, 2022

Topologically penalized regression on manifolds

By Wolfgang Polonik

published on October 5, 2022

Bayesian nonparametric estimation of a density living near an unknown manifold

By Judith Rousseau

published on October 5, 2022

Linear methods for non-linear inverse problems

By Botond Szabo

published on October 6, 2022

Convergence of Sharpness-Aware Minimization

By Peter Bartlett

published on October 6, 2022

Dimensionality reduction in reinforcement learning by randomisation

By Denis Belomestny

published on October 6, 2022

Stein effect for estimating many vector means: a "blessing of dimensionality" phenomenon

By Gilles Blanchard

published on October 6, 2022

On the use of overfitting for estimator selection

By Claire Lacour

published on October 6, 2022

Optimal Permutation estimation in crowdsourcing problems

By Nicolas Verzelen

published on October 7, 2022

What does LIME really see in images?

By Damien Garreau

published on October 7, 2022

A statistical analysis of an image classification problem

By Johannes Schmidt-Hieber

published on October 7, 2022

Learning a partial correlation graph using only a few covariance queries

By Vasiliki Velona

Mathematics
and Interactions

Not Only Scalar Curvature Seminar

ALEA Days / Journées ALEA

Sylvia Serfaty : Systems with Coulomb Interactions

2022 - Francophone Computer Algebra Days - Journées nationales de calcul formel

Collection 2022 - T3 - WS1 - Non-Linear and High Dimensional Inference

Scaling ResNets in the Large-depth Regime

Overcoming the curse of dimensionality with deep neural networks

Learning on and near Low-Dimensional Subsets of the Wasserstein Manifold

Extrinsic and Intrinsic Operator Estimations for Manifold Learning

A graph coupling view of dimension reduction

Topologically penalized regression on manifolds

Bayesian nonparametric estimation of a density living near an unknown manifold

Linear methods for non-linear inverse problems

Convergence of Sharpness-Aware Minimization

Dimensionality reduction in reinforcement learning by randomisation

Stein effect for estimating many vector means: a "blessing of dimensionality" phenomenon

On the use of overfitting for estimator selection

Optimal Permutation estimation in crowdsourcing problems

What does LIME really see in images?

A statistical analysis of an image classification problem

Learning a partial correlation graph using only a few covariance queries

Manifold Learning with Noisy Data

Federated Learning with Communication Constraints: Challenges in Compression Based Approaches

Leveraging Knowledge to Design Machine Learning Despite the Lack of Industrial Data

Interplay between notions of convexity in complex, symplectic and contact geometries

Méthodes automatiques pour la génération aléatoire de structures combinatoires - cours 1/2

Méthodes automatiques pour la génération aléatoire de structures combinatoires - cours 2/2

Et si SAT était vraiment difficile? Quelques conséquences des hypothèses ETH et SETH

Méthodes galoisiennes appliquées aux équations fonctionnelles issues de la combinatoire énumérative