When compressive learning fails: blame the decoder or the sketch?

Schellekens, Vincent;Jacques, Laurent
(2020) iTWIST′20 — Location: Nantes, France (2.December.2020)

Files

200908273.pdf
  • Open Access
  • Adobe PDF
  • 735.65 KB
Download

Details

Authors
Abstract
In compressive learning, a mixture model (a set of centroids or a Gaussian mixture) is learned from a sketch vector, that serves as a highly compressed representation of the dataset. This requires solving a non-convex optimization problem, hence in practice approximate heuristics (such as CLOMPR) are used. In this work we explore, by numerical simulations, properties of this non-convex optimization landscape and those heuristics.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Schellekens, V., & Jacques, L. (2020). When compressive learning fails: blame the decoder or the sketch? in Proceedings of iTWIST′20, Paper-ID: 22, Nantes, France, December, 2-4, 2020. Published. iTWIST′20, Nantes, France. https://hdl.handle.net/2078.5/219838