Papers on Minimally Supervised Learning

Themes: active learning, semi-supervised learning, transfer learning

Working papers:

  • Steve Hanneke, Samory Kpotufe. A No-Free-Lunch Theorem For Multitask Learning.
    [ arXiv ]

  • Nicholas Galbraith, Samory Kpotufe. An Adaptive Classification Tree under Covariate-Shift.

Published papers:

  • Samory Kpotufe, Guillaume Martinet. Marginal Singularity, and the Benefits of Labels in Covariate-Shift.
    Annals of Statistics (to appear) 2021. [ arXiv ]

  • Joe Suk, Samory Kpotufe. Self-Tuning Bandits over Unknown Covariate-Shifts.
    Algorithmic Learning Theory (ALT) 2020. [ arXiv ]

  • Steve Hanneke, Samory Kpotufe. On the Value of Target Data in Transfer Learning.
    Neural Information Processing Systems (NeurIPS) 2019. [ pdf ]

  • Samory Kpotufe, Guillaume Martinet. Marginal Singularity, and the Benefits of Labels in Covariate-Shift.
    Accepted abstract at Conference on Learning Theory (COLT) 2018. [ arXiv ]

  • Andrea Locatelli, Alexandra, Carpentier, Samory Kpotufe. An Adaptive Strategy for Active Learning with Smooth Decision Boundary.
    Algorithmic Learning Theory (ALT) 2018. [ arXiv ]

  • Andrea Locatelli, Alexandra, Carpentier, Samory Kpotufe. Adaptivity to Noise Parameters in Nonparametric Active Learning.
    Conference on Learning Theory (COLT) 2017. [ pdf ]

  • Samory Kpotufe. Lipschitz Density-Ratios, Structured Data, and Data-driven Tuning.
    Artificial Intelligence and Statistics (AISTATS) 2017. [ pdf ]

    (Also listed under Unsupervised Learning)

  • Samory Kpotufe, Ruth Urner, Shai Ben-David. Hierarchical label queries with data-dependent partitions.
    Conference on Learning Theory (COLT) 2015. [ pdf ]