---
res:
  bibo_abstract:
  - "We study the problem of learning from multiple untrusted data sources, a scenario
    of increasing practical relevance given the recent emergence of crowdsourcing
    and collaborative learning paradigms. Specifically, we analyze the situation in
    which a learning system obtains datasets from multiple sources, some of which
    might be biased or even adversarially perturbed. It is\r\nknown that in the single-source
    case, an adversary with the power to corrupt a fixed fraction of the training
    data can prevent PAC-learnability, that is, even in the limit of infinitely much
    training data, no learning system can approach the optimal test error. In this
    work we show that, surprisingly, the same is not true in the multi-source setting,
    where the adversary can arbitrarily\r\ncorrupt a fixed fraction of the data sources.
    Our main results are a generalization bound that provides finite-sample guarantees
    for this learning setting, as well as corresponding lower bounds. Besides establishing
    PAC-learnability our results also show that in a cooperative learning setting
    sharing data with other parties has provable benefits, even if some\r\nparticipants
    are malicious. @eng"
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Nikola H
      foaf_name: Konstantinov, Nikola H
      foaf_surname: Konstantinov
      foaf_workInfoHomepage: http://www.librecat.org/personId=4B9D76E4-F248-11E8-B48F-1D18A9856A87
    orcid: 0009-0009-5204-7621
  - foaf_Person:
      foaf_givenName: Elias
      foaf_name: Frantar, Elias
      foaf_surname: Frantar
      foaf_workInfoHomepage: http://www.librecat.org/personId=09a8f98d-ec99-11ea-ae11-c063a7b7fe5f
  - foaf_Person:
      foaf_givenName: Dan-Adrian
      foaf_name: Alistarh, Dan-Adrian
      foaf_surname: Alistarh
      foaf_workInfoHomepage: http://www.librecat.org/personId=4A899BFC-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0003-3650-940X
  - foaf_Person:
      foaf_givenName: Christoph
      foaf_name: Lampert, Christoph
      foaf_surname: Lampert
      foaf_workInfoHomepage: http://www.librecat.org/personId=40C20FD2-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0001-8622-7887
  bibo_volume: 119
  dct_date: 2020^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2640-3498
  dct_language: eng
  dct_publisher: ML Research Press@
  dct_title: On the sample complexity of adversarial multi-source PAC learning@
...