title

An application of Latin hypercube sampling to optimization - The DO Loop

content-type

text/html; charset=UTF-8

viewport

width=device-width, initial-scale=1

fb:app_id

129959910415506

robots

index, follow, max-image-preview:large, max-snippet:-1, max-video-preview:-1

og:title

An application of Latin hypercube sampling to optimization

og:type

article

og:url

https://blogs.sas.com/content/iml/2025/06/30/latin-hypercube-optimization.html

og:site_name

The DO Loop

og:description

A previous article discusses a "Catch-22" paradox for fitting nonlinear regression models: You can't estimate the parameters until you fit the model, but you can't fit the model until you provide an initial guess for the parameters!

twitter:card

summary_large_image

twitter:title

An application of Latin hypercube sampling to optimization - The DO Loop

twitter:description

A previous article discusses a "Catch-22" paradox for fitting nonlinear regression models: You can't estimate the parameters until you fit the model, but you can't fit the model until you provide an initial guess for the parameters! If your initial guess for the parameters is not good enough, the nonlinear

twitter:image

https://blogs.sas.com/content/iml/files/2025/06/LHSOptim2.png

twitter:creator

@https://twitter.com/RickWicklin

alternate

https://blogs.sas.com/content/iml/feed/json

alternate

https://blogs.sas.com/content/iml/2025/06/30/latin-hypercube-optimization.html/feed/json

canonical

https://blogs.sas.com/content/iml/?p=54725

dns-prefetch

//fonts.googleapis.com

pingback

https://blogs.sas.com/content/iml/xmlrpc.php