Ensmallen: A C++ Library For Efficient Numerical Optimization

Re:Ensmallen: A C++ Library For Efficient Numerical Optimiza... by flemishgun on Wednesday December 08, 2021 @04:59PM (#29491104)

This toolkit was originally part of the mlpack machine learning library (https://github.com/mlpack/mlpack) before it was split out into a separate, standalone effort.

[ Parent | on HN ]

Re:Ensmallen: A C++ Library For Efficient Numerical Optimiza... by amelius on Wednesday December 08, 2021 @05:58PM (#29491680)

Can machine learning be used to do optimization?

What if you applied machine learning to machine learning?

[ Parent | on HN ]

Re:Ensmallen: A C++ Library For Efficient Numerical Optimiza... by nicwilson on Wednesday December 08, 2021 @06:49PM (#29492128)

Yes, you use it to select the parameters of you optimiser, like step size and momentum schedules and other tuneable things. Look up MAML (meta abstract machine learning?)

[ Parent | on HN ]

Re:Ensmallen: A C++ Library For Efficient Numerical Optimiza... by sadfev on Friday December 10, 2021 @09:54AM (#29510556)

11 years ago, I did something like that. I was trying to use particle swarm optimization to efficiently update neural network weights, it didn’t work well.

Don’t ask me why I even tried, I was a dumb but code happy undergrad!

[ Parent | on HN ]