Poster
in
Workshop: Dynamic Neural Networks
SnapStar Algorithm: a new way to ensemble Neural Networks
Sergey Zinchenko · Dmitry Lishudi
Abstract:
We propose a new neural network ensemble algorithm based on Audibert's empirical star algorithm and snapshot technique. We provide optimal theoretical minimax bound on the excess squared risk. Additionally, we empirically study this algorithm on regression and classification tasks and and show that it can be successfully applied to budget construct ensemble.
Chat is not available.