Physical Models and Machine Learning for Scientific Imaging. Seminar at Isterre, Grenoble, 2023.

Image Enhancement from Raw Image Bursts: Some Opportunities for Scientific Imaging. Seminar at Owkin, Paris, 2023.

Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise. SICO workshop, Autrans, 2022.

Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts, French-German Machine Learning Symposium, Munich, online. The video.

Trainable Algorithms for Inverse Imaging Problems, Mathematics of deep learning seminar, Flation Institute/NYU, also given at KU Lueven, online.

Trainable Algorithms for Inverse Imaging Problems, GDR MascotNum, online.

On the Happy Marriage Between Kernel Methods and Deep Learning, DataSig Seminar, Oxford/UCL.

On Accelerated Optimization Methods for Large-Scale
Machine Learning, ICT Innovations (online), Skopje, 2020.

On the Happy Marriage Between Kernel Methods and Deep Learning, MalGA Seminar (online), Genova 2020. The video.

Estimate Sequences for Variance-Reduced Stochastic Composite Optimization. ICCOPT, Berlin, 2019.

Test of time award talk. ICML, 2019. The video.

A Kernel Perspective for Regularizing Deep Neural Networks. Imaging and Machine Learning conference, IHP, 2019. The video.

Invariance and Stability to Deformations of
Deep Convolutional Representations. YES workshop, Eindhoven, 2019.

Invariance and Stability to Deformations of
Deep Convolutional Representations. AI and ML workshop, Telecom ParisTech, 2018.

Invariance and Stability to Deformations of
Deep Convolutional Representations. CEFRL workshop, ECCV, Munich, 2018.

Invariance and Stability to Deformations of
Deep Convolutional Representations. Theory of Deep Learning Workshop, ICML, Stockholm, 2018.

An Inexact Variable Metric PPA
for Generic Quasi-Newton Acceleration, ISMP, Bordeaux, 2018.

Foundations of Deep Learning from a Kernel Point of View. Workshop on the Future of Random Projections, Paris, 2018.

Generic Acceleration Schemes for Gradient-Based Optimization. Seminaire Parisien d'Optimisation, Paris, 2018.

Foundations of Deep Learning from a Kernel Point of View. CoSIP winter school, Berlin, 2017 The video .

A Generic Quasi-Newton Algorithm for Faster Gradient-Based Optimization. JFCO, Toulouse, 2017.

A Generic Quasi-Newton Algorithm for Faster Gradient-Based Optimization. LCCC workshop, Lund, 2017.

Towards Deep Kernel Machines. Pattern Recognition and Computer Vision Colloquium, Prague, 2017.

A Generic Quasi-Newton Algorithm for Faster Gradient-Based Optimization. Les Houches, 2017.

Towards Deep Kernel Machines. Amazon, Berlin, 2017.

Generic Acceleration Schemes for Gradient-Based Optimization. Amazon, Berlin, 2017.

A Generic Quasi-Newton Algorithm for Faster Gradient-Based Optimization. GdR Isis meeting, Telecom ParisTech, 2016.

A universal catalyst for gradient-based optimization. workshop Phi-Tab, Telecom ParisTech, 2016.

Towards deep kernel machines. MAESTRA summer school. Ohrid. 2016. The video .

Sparse estimation for image and vision processing. MAESTRA summer school. Ohrid. 2016. The video .

Complexity analysis of the Lasso regularization path. Journees MAS. Grenoble. 2016.

Proximal Minimization by Incremental Surrogate Optimization (MISO). ICCOPT, Tokyo, 2016.

A universal catalyst for gradient-based optimization. MIA, Paris, 2016.

Sparse Estimation for Image and Vision Processing. BigOptim Summer school, Grenoble, 2015.

Two talks related to sparsity. Statslab seminar, Cambridge, 2015.

Introduction to Parsimony and the complexity of the Lasso regularization path BIG Data, Toulouse, 2014.

Sparse Estimation for Image and Vision Processing DENIS Summer school, Tampere, 2014.

RNA isoforms discovery from RNA-seq data. Persyvact workshop on probabilistic graphical models. Grenoble. 2014.

Incremental and Stochastic Majorization-Minimization Algorithms for Large-Scale Machine Learning. SIAM Optimization. San Diego. 2014.

Complexity analysis of the Lasso regularization path. SIAM Optimization. San Diego. 2014.

Optimization for Sparse Estimation and Structured Sparsity IMA Short Course “Applied Statistics and Machine Learning”, Minneapolis, 2013. s/index.php?id=2299 The video (part I), and part II .

Sparse Estimation and Dictionary Learning (for Biostatistics?) Biostatistics Seminar, UC Berkeley. 2012.

Complexity Analysis of the Lasso Regularization Path ICML 2012. Edinburgh. The video .

Backpropagation rules for sparse coding Sparsity workshop, ICML 2012. Edinburgh.

Structured Sparse Estimation with Network Flow Optimization Neyman seminar. UC Berkeley. February 2012.

Path Coding Penalties in Directed Acyclic Graphs NIPS workshop on optimization for machine learning. Sierra Nevada. December 2011. The video .

Topographic dictionary learning with structured sparsity SPIE conference on wavelets and sparsity XIV, August 2011, San Diego.

Network flow algorithms for structured sparsity ICML workshop on structured sparsity, July 2011, Seattle.

Sparse coding for machine learning, image processing and computer vision. Journees Orasis, June 2011, Praz sur Arly.

Recent Advances in Structured Sparsity LEAR seminar, September 2010, Grenoble.

Sparse Coding and Dictionary Learning for Image Analysis. Visual Recognition and Machine Learning Summer School, 2010, Grenoble.

Non-local Sparse Models for Image Restoration. Oxford, July, 2010.

Tutorial on Sparse Coding and Dictionary Learning for Image Analysis. CVPR 2010. San Francisco

Non-local Sparse Models for Image Restoration. Luminy, May 2010

Non-local Sparse Models for Image Restoration. STATIM 2010, Evry, February 2010

Non-local Sparse Models for Image Restoration Workshop Microsoft-INRIA, January, 2010, Paris.

Tutorial on Sparse Coding and Dictionary Learning for Image Analysis. ICCV 2009. Kyoto. Japan.

Online Dictionary Learning for Sparse Coding. ICML 2009. MontrĂ©al. Canada. The video .

Sparse learned representations for image restoration. part 1. part 2. The video ., Symposium Patch-based Image Representation, Manifolds and Sparsity, 2009. Rennes.