298 citations · 626 across the 17 of their papers we have counts for
6 papers · 1 filter
Unveiling the Latent Space Geometry of Push-Forward Generative Models
Thibaut Issenhuth, Ugo Tanielian, Jérémie Mary +1
Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encode…
Lessons from the AdKDD'21 Privacy-Preserving ML Challenge
Eustache Diemert, Romain Fabre, Alexandre Gilotte +6
Designing data sharing mechanisms providing performance and strong privacy guarantees is a hot topic for the Online Advertising industry. Namely, a prominent proposal discussed und…
Latent reweighting, an almost free improvement for GANs
Thibaut Issenhuth, Ugo Tanielian, David Picard +1
Standard formulations of GANs, where a continuous function deforms a connected latent space, have been shown to be misspecified when fitting different classes of images. In particu…
Hybrid Recommender System based on Autoencoders
Florian Strub, Romaric Gaudel, Jérémie Mary
A standard model for Recommender Systems is the Matrix Completion setting: given partially known matrix of ratings given by users (rows) to items (columns), infer the unknown ratin…
Bandits Warm-up Cold Recommender Systems
Jérémie Mary, Romaric Gaudel, Preux Philippe
We address the cold start problem in recommendation systems assuming no contextual information is available neither about users, nor items. We consider the case in which we only ha…
Reducing statistical time-series problems to binary classification
Daniil Ryabko, Jérémie Mary
We show how binary classification methods developed to work on i.i.d. data can be used for solving statistical problems that are seemingly unrelated to classification and concern h…