Parameter Optimization using Simulated Annealing

2 ビュー (過去 30 日間)
MByk
MByk 2017 年 12 月 18 日
コメント済み: MByk 2017 年 12 月 18 日
I am new to optimization and trying to understand the basics, so sorry if it is a dumb question. Is it possible to tune parameters (which is a search problem) of a classifier using simulated annealing or other optimization technique, just for an example optimum value of "k" in KNN (I know there is an automatic hyperparameter optimization for KNN)?

採用された回答

Alan Weiss
Alan Weiss 2017 年 12 月 18 日
編集済み: Alan Weiss 2017 年 12 月 18 日
Sure, you can do anything you want. It might not be a good idea, but feel free.
Write an objective function that is, say, the cross-validation error rate for a particular parameter. If you have k as your parameter, and a cross-valudation partition c, then you might have
fun = @(k)kfoldLoss(fitcknn(X,y,'CVPartition',c,...
'NumNeighbors',k));
The only problem with this is that k is an integer variable, and most optimizers (including simulannealbnd) work only with continuous parameters. But you could use mixed-integer ga to optimize this.
Good luck,
Alan Weiss
MATLAB mathematical toolbox documentation
  1 件のコメント
MByk
MByk 2017 年 12 月 18 日
Thank you very much greatly appreciated.

サインインしてコメントする。

その他の回答 (0 件)

カテゴリ

Help Center および File ExchangeSimulated Annealing についてさらに検索

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by