pith. sign in

arxiv: 1803.06586 · v1 · pith:A346TKDBnew · submitted 2018-03-17 · 💻 cs.LG · stat.ML

Structural query-by-committee

classification 💻 cs.LG stat.ML
keywords learningquery-by-committeeactivealgorithmconsistencyconvergencedescribedifferent
0
0 comments X
read the original abstract

In this work, we describe a framework that unifies many different interactive learning tasks. We present a generalization of the {\it query-by-committee} active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.