Stable and Efficient Gaussian Process Calculations
The use of Gaussian processes can be an effective approach to prediction in a supervised learning environment. For large data sets, the standard Gaussian process approach requires solving very large systems of linear equations and approximations are required for the calculations to be practical. We will focus on the subset of regressors approximation technique. We will demonstrate that there can be numerical instabilities in a well known implementation of the technique. We discuss alternate implementations that have better numerical stability properties and can lead to better predictions. Our results will be illustrated by looking at an application involving prediction of galaxy redshift from broadband spectrum data.
Resources
4 resources available
-
View this dataset's algorithm theoretical basis document
HTML -
View information related to this dataset
HTML -
Download this dataset through a directory map
HTML -
View this dataset's processing history
HTML
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| accrualPeriodicity | irregular |
| bureauCode |
[
"026:00"
]
|
| contactPoint |
{
"fn": "undefined",
"@type": "vcard:Contact",
"hasEmail": "mailto:sdps@oceancolor.gsfc.nasa.gov"
}
|
| description | The use of Gaussian processes can be an effective approach to prediction in a supervised learning environment. For large data sets, the standard Gaussian process approach requires solving very large systems of linear equations and approximations are required for the calculations to be practical. We will focus on the subset of regressors approximation technique. We will demonstrate that there can be numerical instabilities in a well known implementation of the technique. We discuss alternate implementations that have better numerical stability properties and can lead to better predictions. Our results will be illustrated by looking at an application involving prediction of galaxy redshift from broadband spectrum data. |
| distribution |
[
{
"@type": "dcat:Distribution",
"title": "View this dataset's algorithm theoretical basis document",
"format": "HTML",
"mediaType": "text/html",
"description": "NASA Ocean Color Web - Algorithm Description Documentation",
"downloadURL": "https://oceancolor.gsfc.nasa.gov/resources/atbd/"
},
{
"@type": "dcat:Distribution",
"title": "View information related to this dataset",
"format": "HTML",
"mediaType": "text/html",
"description": "NASA Ocean Color Web - Data Citation Guidelines",
"downloadURL": "https://oceancolor.gsfc.nasa.gov/resources/how-to-cite/"
},
{
"@type": "dcat:Distribution",
"title": "Download this dataset through a directory map",
"format": "HTML",
"mediaType": "text/html",
"description": "NASA Ocean Color Web - Data Distribution Site",
"downloadURL": "https://oceandata.sci.gsfc.nasa.gov/directdataaccess/Level-2/SNPP-VIIRS/"
},
{
"@type": "dcat:Distribution",
"title": "View this dataset's processing history",
"format": "HTML",
"mediaType": "text/html",
"description": "NASA Ocean Color Web - Processing History",
"downloadURL": "https://oceancolor.gsfc.nasa.gov/data/reprocessing/"
}
]
|
| identifier | DASHLINK_153 |
| issued | 2010-09-22 |
| keyword |
[
"ames",
"dashlink",
"nasa"
]
|
| landingPage | https://c3.nasa.gov/dashlink/resources/153/ |
| modified | 2025-03-31 |
| programCode |
[
"026:029"
]
|
| publisher |
{
"name": "Dashlink",
"@type": "org:Organization"
}
|
| title | Stable and Efficient Gaussian Process Calculations |
