ChanServ changed the topic of #mlpack to: "mlpack: a fast, flexible machine learning library :: We don't always respond instantly, but we will respond; please be patient :: Logs at http://www.mlpack.org/irc/
anoop has quit [Remote host closed the connection]
lozhnikov has quit [Ping timeout: 250 seconds]
lozhnikov has joined #mlpack
xiaohong_ has joined #mlpack
xiaohong has quit [Read error: Connection reset by peer]
xiaohong_ has quit [Remote host closed the connection]
xiaohong has joined #mlpack
xiaohong has quit [Remote host closed the connection]
xiaohong has joined #mlpack
ankit3699 has joined #mlpack
xiaohong has quit [Remote host closed the connection]
< rcurtin>
awesome, I will merge then since it has two approvals
< rcurtin>
but I didn't want to jump into a PR I was not involved with :)
ankit3699 has joined #mlpack
< metahost>
Are genetic algorithms planned for ensmallen?
< metahost>
I have seen CNE and DE optimizers available for non-differentiable functions
< zoq>
metahost: Absolutely, already looked into NSGA-II but haven't had the time yet to work on an implementation.
ImQ009 has quit [Quit: Leaving]
< rcurtin>
seems like that would be a great fit for the categorical function types (at least the "traditional" genetic algorithms)
< rcurtin>
in fact maybe I should open some issues for, e.g., extending simulated annealing to categorical functions
< rcurtin>
I met with an old mlpack contributor recently; he's connected to people doing the IBM LALE auto-ML project, and they had interest in wrapping mlpack and also using ensmallen for hyperparameter optimization
< rcurtin>
so perhaps there could be a lot of momentum for categorical function optimization
< rcurtin>
or at least that's something I've always found exciting :)
ankit3699 has quit [Quit: This computer has gone to sleep]