• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail

Radon Sobolev Variational Auto-Encoders

Turinici, Gabriel (2021), Radon Sobolev Variational Auto-Encoders, Neural Networks, 141, p. 294-305. 10.1016/j.neunet.2021.04.018

View/Open
163541413353053.pdf (1.489Mb)
Type
Article accepté pour publication ou publié
Date
2021
Journal name
Neural Networks
Volume
141
Publisher
Elsevier
Pages
294-305
Publication identifier
10.1016/j.neunet.2021.04.018
Metadata
Show full item record
Author(s)
Turinici, Gabriel cc
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)
The quality of generative models (such as Generative adversarial networks and Variational Auto-Encoders) depends heavily on the choice of a good probability distance. However some popular metrics like the Wasserstein or the Sliced Wasserstein distances, the Jensen–Shannon divergence, the Kullback–Leibler divergence, lack convenient properties such as (geodesic) convexity, fast evaluation and so on. To address these shortcomings, we introduce a class of distances that have built-in convexity. We investigate the relationship with some known paradigms (sliced distances – a synonym for Radon distances – reproducing kernel Hilbert spaces, energy distances). The distances are shown to possess fast implementations and are included in an adapted Variational Auto-Encoder termed Radon–Sobolev Variational Auto-Encoder (RS-VAE) which produces high quality results on standard generative datasets.
Subjects / Keywords
Variational Auto-Encoder; Generative model; Sobolev spaces; Radon Sobolev Variational Auto-Encoder

Related items

Showing items related by title and author.

  • Thumbnail
    X-Ray Sobolev Variational Auto-Encoders 
    Turinici, Gabriel (2019) Document de travail / Working paper
  • Thumbnail
    Deep learning of Value at Risk through generative neural network models : the case of the Variational Auto Encoder 
    Brugière, Pierre; Turinici, Gabriel (2022) Document de travail / Working paper
  • Thumbnail
    Singular evolution on maniforlds, their smoothing properties, and Sobolev inequalities 
    Bonforte, Matteo; Grillo, Gabriele (2007) Article accepté pour publication ou publié
  • Thumbnail
    Geodesics on Shape Spaces with Bounded Variation and Sobolev Metrics 
    Nardi, Giacomo; Peyré, Gabriel; Vialard, François-Xavier (2016) Article accepté pour publication ou publié
  • Thumbnail
    Variational methods in imaging and geometric control 
    Bergounioux, Maïtine; Peyré, Gabriel; Schnörr, Christoph; Caillau, Jean-Baptiste; Haberkorn, Thomas (2017-01) Ouvrage
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo