Learning from Biased Data: A Semi-Parametric Approach

Patrice Bertail · Stephan Clémençon · Yannick Guyonvarch · Nathan NOIRY

[ Abstract ] [ Livestream: Visit Learning Theory 6 ] [ Paper ]
Wed 21 Jul 7:20 a.m. — 7:25 a.m. PDT

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< \! \!

Chat is not available.