leave-some-out cross-validation

initialism: LSO
https://doi.org/10.1351/goldbook.11461
A form of cross-validation in which more than one observation is left out at each run. Typically many runs with random samplings are performed.
Source:
PAC, 2016, 88, 239. (Glossary of terms used in computational drug design, part II (IUPAC Recommendations 2015)) on page 249 [Terms] [Paper]