---
res:
  bibo_abstract:
  - "Because of the increasing popularity of machine learning methods, it is becoming
    important to understand the impact of learned components on automated decision-making
    systems and to guarantee that their consequences are beneficial to society. In
    other words, it is necessary to ensure that machine learning is sufficiently trustworthy
    to be used in real-world applications. This thesis studies two properties of machine
    learning models that are highly desirable for the\r\nsake of reliability: robustness
    and fairness. In the first part of the thesis we study the robustness of learning
    algorithms to training data corruption. Previous work has shown that machine learning
    models are vulnerable to a range\r\nof training set issues, varying from label
    noise through systematic biases to worst-case data manipulations. This is an especially
    relevant problem from a present perspective, since modern machine learning methods
    are particularly data hungry and therefore practitioners often have to rely on
    data collected from various external sources, e.g. from the Internet, from app
    users or via crowdsourcing. Naturally, such sources vary greatly in the quality
    and reliability of the\r\ndata they provide. With these considerations in mind,
    we study the problem of designing machine learning algorithms that are robust
    to corruptions in data coming from multiple sources. We show that, in contrast
    to the case of a single dataset with outliers, successful learning within this
    model is possible both theoretically and practically, even under worst-case data
    corruptions. The second part of this thesis deals with fairness-aware machine
    learning. There are multiple areas where machine learning models have shown promising
    results, but where careful considerations are required, in order to avoid discrimanative
    decisions taken by such learned components. Ensuring fairness can be particularly
    challenging, because real-world training datasets are expected to contain various
    forms of historical bias that may affect the learning process. In this thesis
    we show that data corruption can indeed render the problem of achieving fairness
    impossible, by tightly characterizing the theoretical limits of fair learning
    under worst-case data manipulations. However, assuming access to clean data, we
    also show how fairness-aware learning can be made practical in contexts beyond
    binary classification, in particular in the challenging learning to rank setting.@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
  bibo_doi: 10.15479/at:ista:10799
  dct_date: 2022^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2663-337X
  - http://id.crossref.org/issn/978-3-99078-015-2
  dct_language: eng
  dct_publisher: Institute of Science and Technology Austria@
  dct_subject:
  - robustness
  - fairness
  - machine learning
  - PAC learning
  - adversarial learning
  dct_title: Robustness and fairness in machine learning@
...