---
res:
  bibo_abstract:
  - "Large-scale deep learning models are known to memorize parts of the training\r\nset.
    In machine learning theory, memorization is often framed as interpolation or\r\nlabel
    fitting, and classical results show that this can be achieved when the number\r\nof
    parameters p in the model is larger than the number of training samples n. In\r\nthis
    work, we consider memorization from the perspective of data reconstruction,\r\ndemonstrating
    that this can be achieved when p is larger than dn, where d is\r\nthe dimensionality
    of the data. More specifically, we show that, in the random\r\nfeatures model,
    when p ≫ dn, the subspace spanned by the training samples in\r\nfeature space
    gives sufficient information to identify the individual samples in input\r\nspace.
    Our analysis suggests an optimization method to reconstruct the dataset\r\nfrom
    the model parameters, and we demonstrate that this method performs well on\r\nvarious
    architectures (random features, two-layer fully-connected and deep residual\r\nnetworks).
    Our results reveal a law of data reconstruction, according to which the\r\nentire
    training dataset can be recovered as p exceeds the threshold dn.\r\n@eng"
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Leonardo
      foaf_name: Iurada, Leonardo
      foaf_surname: Iurada
  - foaf_Person:
      foaf_givenName: Simone
      foaf_name: Bombari, Simone
      foaf_surname: Bombari
      foaf_workInfoHomepage: http://www.librecat.org/personId=ca726dda-de17-11ea-bc14-f9da834f63aa
  - foaf_Person:
      foaf_givenName: Tatiana
      foaf_name: Tommasi, Tatiana
      foaf_surname: Tommasi
  - 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: 2026
  dct_date: 2026^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/9798331339678
  dct_language: eng
  dct_publisher: OpenReview@
  dct_title: A law of data reconstruction for random features (and beyond)@
...