bayesian-optimization Review

0 0

Review of bayesian-optimization powered by the Slant community.

"Bayesian Optimization" is a pure Python implementation of bayesian global optimization with gaussian processes, available on GitHub.

SpecsUpdate

Quasi Random SearchNo

Pypi PackageYes

Bayesian Optimization SearchYes

Continuous VariablesYes

CMAES SearchNo

Evaluation Cost Sensitive SearchNo

Random SearchNo

Grid SearchNo

MOCMAES SearchNo

Integer VariablesNo

Categorical VariablesNo

Ranked in these QuestionsQuestion Ranking

What are the best Python hyperparameter optimization frameworks?

Pros

Pro
Documentation includes code to allow easy visualization

The Jupyter notebook is here.

Note that this is a snapshot from a fixed revision. You can get the latest here.

Cons

Con
Bayesian optimization requires making a smoothness assumption

The Bayesian optimization implementation needs the user to specify a kernel width that determines how smooth the system assumes functions will be with no data. Other implementations do not require this assumption and integrate out the smoothness assumption using Markov Chain Monte Carlo (MCMC) sampling.

The choice here is the width of a Matern kernel which, if you have to have one, is a more flexible kernel than the more commonly found Squared Exponential kernel.

Built By the Slant team

Find the best product instantly.

4.7 star rating

Try it now - it's free