• 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

Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks

Hu, Kaitong; Ren, Zhenjie; Siska, David; Szpruch, Lukasz (2019-05), Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks. https://basepub.dauphine.fr/handle/123456789/19858

View/Open
1905.07769(1).pdf (419.4Kb)
Type
Document de travail / Working paper
Date
2019-05
Publisher
Cahier de recherche CEREMADE, Université Paris-Dauphine
Series title
Cahier de recherche CEREMADE, Université Paris-Dauphine
Published in
Paris
Pages
29
Metadata
Show full item record
Author(s)
Hu, Kaitong
Centre de Mathématiques Appliquées - Ecole Polytechnique [CMAP]
Ren, Zhenjie
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Siska, David
School of Mathematics - University of Edinburgh
Szpruch, Lukasz
School of Mathematics - University of Edinburgh
Abstract (EN)
We present a probabilistic analysis of the long-time behaviour of the nonlocal, diffusive equations with a gradient flow structure in 2-Wasserstein metric, namely, the Mean-Field Langevin Dynamics (MFLD). Our work is motivated by a desire to provide a theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as training of deep neural networks. The key insight is that the certain class of the finite dimensional non-convex problems becomes convex when lifted to infinite dimensional space of measures. We leverage this observation and show that the corresponding energy functional defined on the space of probability measures has a unique minimiser which can be characterised by a first order condition using the notion of linear functional derivative. Next, we show that the flow of marginal laws induced by the MFLD converges to the stationary distribution which is exactly the minimiser of the energy functional. We show that this convergence is exponential under conditions that are satisfied for highly regularised learning tasks. At the heart of our analysis is a pathwise perspective on Otto calculus used in gradient flow literature which is of independent interest. Our proof of convergence to stationary probability measure is novel and it relies on a generalisation of LaSalle's invariance principle. Importantly we do not assume that interaction potential of MFLD is of convolution type nor that has any particular symmetric structure. This is critical for applications. Finally, we show that the error between finite dimensional optimisation problem and its infinite dimensional limit is of order one over the number of parameters.
Subjects / Keywords
Mean-Field Langevin Dynamics; Gradient Flow; Neural Networks

Related items

Showing items related by title and author.

  • Thumbnail
    Mean-field Langevin System, Optimal Control and Deep Neural Networks 
    Hu, Kaitong; Kazeykina, Anna; Ren, Zhenjie (2019-09) Document de travail / Working paper
  • Thumbnail
    Game on Random Environement, Mean-field Langevin System and Neural Networks 
    Conforti, Giovanni; Kazeykina, Anna; Ren, Zhenjie (2020) Document de travail / Working paper
  • Thumbnail
    Ergodicity of the underdamped mean-field Langevin dynamics 
    Kazeykina, Anna; Ren, Zhenjie; Tan, Xiaolu; Yang, Junjian (2020) Document de travail / Working paper
  • Thumbnail
    The entry and exit game in the electricity markets: A mean-field game approach 
    Aïd, René; Dumitrescu, Roxana; Tankov, Peter (2021) Article accepté pour publication ou publié
  • Thumbnail
    Dynamic Pricing of New Products in Competitive Markets: A Mean-Field Game Approach 
    Chenavaz, Régis; Paraschiv, Corina; Turinici, Gabriel (2021) Article accepté pour publication ou publié
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