---
res:
  bibo_abstract:
  - Autoencoders are a popular model in many branches of machine learning and lossy
    data compression. However, their fundamental limits, the performance of gradient
    methods and the features learnt during optimization remain poorly understood,
    even in the two-layer setting. In fact, earlier work has considered either linear
    autoencoders or specific training regimes (leading to vanishing or diverging compression
    rates). Our paper addresses this gap by focusing on non-linear two-layer autoencoders
    trained in the challenging proportional regime in which the input dimension scales
    linearly with the size of the representation. Our results characterize the minimizers
    of the population risk, and show that such minimizers are achieved by gradient
    methods; their structure is also unveiled, thus leading to a concise description
    of the features obtained via training. For the special case of a sign activation
    function, our analysis establishes the fundamental limits for the lossy compression
    of Gaussian sources via (shallow) autoencoders. Finally, while the results are
    proved for Gaussian data, numerical simulations on standard datasets display the
    universality of the theoretical predictions.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Aleksandr
      foaf_name: Shevchenko, Aleksandr
      foaf_surname: Shevchenko
      foaf_workInfoHomepage: http://www.librecat.org/personId=F2B06EC2-C99E-11E9-89F0-752EE6697425
  - foaf_Person:
      foaf_givenName: Kevin
      foaf_name: Kögler, Kevin
      foaf_surname: Kögler
      foaf_workInfoHomepage: http://www.librecat.org/personId=94ec913c-dc85-11ea-9058-e5051ab2428b
  - foaf_Person:
      foaf_givenName: Hamed
      foaf_name: Hassani, Hamed
      foaf_surname: Hassani
  - foaf_Person:
      foaf_givenName: Marco
      foaf_name: Mondelli, Marco
      foaf_surname: Mondelli
      foaf_workInfoHomepage: http://www.librecat.org/personId=27EB676C-8706-11E9-9510-7717E6697425
    orcid: 0000-0002-3242-7020
  bibo_volume: 202
  dct_date: 2023^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2640-3498
  dct_language: eng
  dct_publisher: ML Research Press@
  dct_title: Fundamental limits of two-layer autoencoders, and achieving them with
    gradient methods@
...
