BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
X-ORIGINAL-URL:https://www.greyc.fr
X-WR-CALDESC:évènements pour GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20261001T140000
DTEND;TZID=Europe/Paris:20261001T153000
DTSTAMP:20261030T135633
CREATED:20260904T113211Z
LAST-MODIFIED:20260925T121328Z
UID:12351-1790863200-1790868600@www.greyc.fr
SUMMARY:Séminaire Image: Converge to optima without overparameterization - Rayleigh quotients and subnetwork tracking par David A. R. Robin
DESCRIPTION:Nous aurons le plaisir d’écouter David A. R. Robin \, Postdoc au LAMSADE (Université Paris Dauphine).\nIl donnera un séminaire IMAGE le jeudi 1er octobre 2026 à 14h en salle de séminaire F-200. \nTitre : « Converge to optima without overparameterization – Rayleigh quotients and subnetwork tracking » \nRésumé :  \nThe Neural Tangent Kernel (NTK) is a central object used to prove convergence of sufficiently overparameterized neural networks to zero training loss. When the NTK of a network is nearly-constant and positive definite\, it decomposes the target signal along its eigenbasis\, explains at which speed each component is learned\, and even accurately predicts generalization error as a function of the target signal’s NTK-induced complexity. But this powerful tool comes with built-in drawbacks: it immediately breaks without overparameterization (such as with infinite samples by data augmentation)\, and its formal construction is essentially restricted to architectures resembling MLPs\, far from the more complicated transformer and attention-based modern architectures. \nIn this talk\, we will explore two ideas to patch these drawbacks: weakening positive-definiteness to a lower-bounded Rayleigh quotient\, and extending to branching architectures by defining and tracking subnetworks across the training trajectory. This will lead us to a more geometric interpretation of neural network dynamics\, with intuitions coming from the geometry of function spaces and discrete random graphs. We will see how this yields convergence proofs to (or near) global optima\, even for infinite datasets and including transformer-based deep architectures\, and discuss the next challenges along the road to quantitative predictions of convergence in modern settings.
URL:https://www.greyc.fr/event/seminaire-image-converge-to-optima-without-overparameterization-rayleigh-quotients-and-subnetwork-tracking-par-david-robin/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:General,Image,Seminaire Image
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20261022T140000
DTEND;TZID=Europe/Paris:20261022T153000
DTSTAMP:20261030T135633
CREATED:20261019T081713Z
LAST-MODIFIED:20261019T081713Z
UID:12386-1792677600-1792683000@www.greyc.fr
SUMMARY:Séminaire Image: Denoising image geometry\, from sparse estimators to neural network denoisers par Nathanael Cuvelle--Magar
DESCRIPTION:Nous aurons le plaisir d’écouter Nathanael Cuvelle–Magar.\nIl donnera un séminaire IMAGE le jeudi 22 octobre 2026 à 14h en salle de séminaire F-200. \nTitre : « Denoising image geometry\, from sparse estimators to neural network denoisers » \nRésumé :  \nDenoising (white noise) has historically been a central task in signal processing\, and is today at the heart of generative diffusion models. This talk focuses on denoising the geometry of images\, understood in the sense of anisotropic regularity along lower-dimensional substructures\, e.g. a contour. For such regularity\, sparse estimators in frames have been shown to be asymptotically optimal\, but deep neural networks have recently achieved substantially stronger numerical performance.\nIn a first part\, we introduce a denoiser for cartoon images based on a wavelet scattering transform\, a simplified convolutional neural network model\, and study its properties. We show how joint minimization and maximization of scattering L1 norms adaptively capture different types of geometric regularity. In a second part\, we compare two of the most prominent architectures used for neural network denoisers\, UNet and Transformer. Despite strong empirical performance\, it remains unclear how they achieve it\, at what parameter cost\, and what role attention plays. For both architectures\, we derive parameter scaling to optimally denoise a Gaussian Mixture Model of geometry and show that attention offers an asymptotic advantage to the Transformer over the UNet. We further show how full quadratic attention can be sparsified\, its complexity reduced to quasi-linear\, thanks to the multiscale structure of geometric regularity. Numerical experiments on real-world datasets support that this result carries over beyond the idealized setting in which it was derived.
URL:https://www.greyc.fr/event/seminaire-image-denoising-image-geometry-from-sparse-estimators-to-neural-network-denoisers-par-nathanael-cuvelle-magar/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:General,Image,News,Seminaire Image
END:VEVENT
END:VCALENDAR