Algorithms for Hyper-Parameter Optimization - NeurIPS

Algorithms for Hyper-Parameter Optimization James Bergstra Re mi Bardenet The Rowland Institute Laboratoire de Recherche en Informatique Harvard University Universite Paris-Sud Yoshua Bengio Bala zs Ke gl De pt. d'Informatique et Recherche Ope rationelle Linear Accelerator Laboratory Universite de Montre al Universite Paris-Sud, CNRS. Abstract Several recent advances to the state of the art in image classification benchmarks have come from better configurations of existing techniques rather than novel ap- proaches to feature learning. Traditionally, Hyper-Parameter Optimization has been the job of humans because they can be very efficient in regimes where only a few trials are possible.

tion of CPU cycles includes more hyper-parameter exploration than has been typical in the machine learning literature. Hyper-parameter optimization is the problem of optimizing a loss function over a graph-structured configuration space. In this work we restrict ourselves to tree-structured configuration spaces. Con-

Loading..

Tags:

  Into, Parameters, Algorithm, Optimization, Hyper, Algorithms for hyper parameter optimization

Information