{"id":261,"date":"2022-03-23T03:16:09","date_gmt":"2022-03-23T03:16:09","guid":{"rendered":"http:\/\/aurimas.eu\/blog\/?p=261"},"modified":"2022-11-10T04:17:57","modified_gmt":"2022-11-10T04:17:57","slug":"intro-to-gaussian-processes","status":"publish","type":"post","link":"https:\/\/aurimas.eu\/blog\/2022\/03\/intro-to-gaussian-processes\/","title":{"rendered":"Gaussian Processes: a versatile data science method that packs infinite dimensions"},"content":{"rendered":"\n
\n
\n
\n
\n<\/div>\n
\n<\/div>
\n

Introduction\u00b6<\/a><\/h2>

One of the most basic problems in data science goes something like this:<\/p>\n

I want to fit a curve to data that is flexible enough to capture non-linear relationships (i.e. go through known data points without any error) but I also want confidence intervals for predictions at unknown points.<\/p>\n<\/blockquote>\n

Most methods give you one or the other. You can go with linear\/polynomial regresssions and have confidence intervals, but they won't perfectly fit your data. Or you can go with splines, LOESS and other non-parametric methods, but then you won't get confidence intervals out of the box (you still can estimate them with bootstrapping but it's not always straightforward).<\/p>\n

It was in this context that I learned about Gaussian Processes (GPs) first. GPs give you both a perfect interpolating function over known data points while also providing variance estimates at unknown data points. Here's a very basic (and recognizable) illustration of a GP in action.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>

\n\n<\/div>
\n\n
\n
\n<\/div>\n
\n
\n
Out[\u00a0]:<\/div>\n
\n
<\/div>\n