About the seminar

This seminar aims to increase the links between the different laboratories in Saclay in the field of Applied Maths, Statistics and Machine Learning. The Seminar is organized every first Tuesday of the month with 2 presentations followed by a small refreshment. The localization of the seminar will change to accommodate the different labs.

Organization

Due to access restriction, you need to register for the seminar. A link is provided in the description and should also be sent with the seminar announcement. It will also help us organize for the food quantities. If you think you will come, please register! (even if you are unsure)

To not miss the next seminar, please subscribe to the announcement mailing list palaisien@inria.fr.
You can also add the calendar from the seminar to your own calendar (see below).

Next seminars

REGISTER 05 Mar 2024, 12h At Inria - Salle Gilles Kahn
Austin Stromme - Minimum intrinsic dimension scaling for entropic optimal transport
Entropic optimal transport (entropic OT) is a regularized variant of the optimal transport problem, widely used in practice for its computational benefits. A key statistical question for both entropic and un-regularized OT is the extent to which low-dimensional structure, of the type conjectured by the well-known manifold hypothesis, affects the statistical rates of convergence. In this talk, we will present statistical results for entropic OT which clarify the statistical role of...
Entropic optimal transport (entropic OT) is a regularized variant of the optimal transport problem, widely used in practice for its computational benefits. A key statistical question for both entropic and un-regularized OT is the extent to which low-dimensional structure, of the type conjectured by the well-known manifold hypothesis, affects the statistical rates of convergence. In this talk, we will present statistical results for entropic OT which clarify the statistical role of intrinsic dimension, and indeed entropic regularization itself, in the form of a novel type of intrinsic dimension dependence we term Minimum Intrinsic Dimension Scaling (MID scaling).
Badr-Eddine Cherief Abdellatif - A PAC-Bayes perspective on learning and generalization
Born in the late 20th century, PAC-Bayes has recently re-emerged as a powerful framework for learning with guarantees. Its bounds offer a principled way to understand the generalization ability of randomized learning algorithms, even guiding the design of new ones. This introduction dives into the foundations of PAC-Bayes, explores its recent advancements, and tries to offer some insights into promising future research directions.
Born in the late 20th century, PAC-Bayes has recently re-emerged as a powerful framework for learning with guarantees. Its bounds offer a principled way to understand the generalization ability of randomized learning algorithms, even guiding the design of new ones. This introduction dives into the foundations of PAC-Bayes, explores its recent advancements, and tries to offer some insights into promising future research directions.
REGISTER 02 Apr 2024, 12h At ENSAE - Salle 1001
Ulugbek Kamilov - Restoration Deep Network as Implicit Priors for Imaging Inverse Problems
Many interesting computational imaging problems can be formulated as imaging inverse problems. Since these problems are often ill-posed, one needs to integrate all the available prior knowledge for obtaining high-quality solutions. This talk focuses on the class of methods based on using “image restoration” deep neural network as data-driven implicit priors on images. The roots of the methods discussed in this talk can be traced to the popular Plug-and-Play Priors (PnP) family of methods for...
Many interesting computational imaging problems can be formulated as imaging inverse problems.
Since these problems are often ill-posed, one needs to integrate all the available prior knowledge for
obtaining high-quality solutions. This talk focuses on the class of methods based on using “image
restoration” deep neural network as data-driven implicit priors on images. The roots of the methods
discussed in this talk can be traced to the popular Plug-and-Play Priors (PnP) family of methods for
solving inverse problems. The talk will present applications of learned implicit priors for image
generation in limited angle computed tomography, recovery of continuously represented microscopy
images, and solving blind inverse problems in magnetic resonance imaging.
TBA
TBA

Scientific Committee

The program and the organization of this seminar is driven by a scientific committee composed of members of the different laboratories in Saclay. The members of the committee are currently:

Funding

This seminar is made possible with financial support of the ENSAE and DataIA.