> Details

Mourrat, Jean Christophe [Author] ; Perkins, Edwin (Organization) [Other]; Addario-Berry, Louigi (Moderation, Organization) [Other]; Angel, Omer (Organization) [Other]; Hernandez-Torres, Sarai (Organization) [Other]; Hughes, Thomas (Organization) [Other]

1/3 Rank-one matrix estimation and Hamilton-Jacobi equations

Reference
management

Bookmarks

Remove from
bookmarks

Share this on Whatsapp

Close

Bookmarks



You can manage bookmarks using lists, please log in to your user account for this.
  • Media type: E-Book; Video
  • Title: 1/3 Rank-one matrix estimation and Hamilton-Jacobi equations
  • Contributor: Mourrat, Jean Christophe [Author]; Perkins, Edwin (Organization) [Other]; Addario-Berry, Louigi (Moderation, Organization) [Other]; Angel, Omer (Organization) [Other]; Hernandez-Torres, Sarai (Organization) [Other]; Hughes, Thomas (Organization) [Other]
  • Published: [Erscheinungsort nicht ermittelbar]: Banff International Research Station (BIRS) for Mathematical Innovation and Discovery, 2020
  • Published in: Online Open Probability School (20ss230) ; (Jan. 2020)
  • Extent: 1 Online-Ressource (120 MB, 01:07:36:28)
  • Language: English
  • DOI: 10.5446/55636
  • Identifier:
  • Origination:
  • Footnote: Audiovisuelles Material
  • Description: We consider the problem of estimating a large rank-one matrix, given noisy observations. This inference problem is known to have a phase transition, in the sense that the partial recovery of the original matrix is only possible if the signal-to-noise ratio exceeds a (non-zero) value. We will present a new proof of this fact based on the study of a Hamilton-Jacobi equation. This alternative argument allows to obtain better rates of convergence, and also seems more amenable to extensions to other models such as spin glasses
  • Access State: Open Access
  • Rights information: Attribution - Non Commercial (CC BY-NC)