Learning from Biased Data: A Semi-Parametric Approach
Patrice Bertail ⋅ Stephan Clémençon ⋅ Yannick Guyonvarch ⋅ Nathan NOIRY
Keywords:
Fairness, Accountability, and Transparency
Theory
Privacy, Anonymity, and Security
Algorithms -> Clustering; Applications -> Hardware and Systems; Applications
2021 Spotlight
Abstract
We consider risk minimization problems where the (source) distribution $P_S$ of the training observations $Z_1, \ldots, Z_n$ differs from the (target) distribution $P_T$ involved in the risk that one seeks to minimize. Under the natural assumption that $P_S$ dominates $P_T$, \textit{i.e.} $P_T< \! \!
Video
Chat is not available.
Successful Page Load