Reference documentation and code samples for the Vertex AI v1beta1 API enum StudySpec.Types.MeasurementSelectionType.
This indicates which measurement to use if/when the service automatically
selects the final measurement from previously reported intermediate
measurements. Choose this based on two considerations:
A) Do you expect your measurements to monotonically improve?
If so, choose LAST_MEASUREMENT. On the other hand, if you're in a
situation where your system can "over-train" and you expect the
performance to get better for a while but then start declining,
choose BEST_MEASUREMENT.
B) Are your measurements significantly noisy and/or irreproducible?
If so, BEST_MEASUREMENT will tend to be over-optimistic, and it
may be better to choose LAST_MEASUREMENT.
If both or neither of (A) and (B) apply, it doesn't matter which
selection type is chosen.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThis document provides reference information for the \u003ccode\u003eStudySpec.Types.MeasurementSelectionType\u003c/code\u003e enum within the Vertex AI v1beta1 API, specifically in the Google.Cloud.AIPlatform.V1Beta1 namespace.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eMeasurementSelectionType\u003c/code\u003e enum determines how the service selects a final measurement from intermediate measurements, considering factors such as whether improvements are expected to be monotonic or if measurements are noisy.\u003c/p\u003e\n"],["\u003cp\u003eThe enum offers three fields: \u003ccode\u003eBestMeasurement\u003c/code\u003e for selecting the best reported measurement, \u003ccode\u003eLastMeasurement\u003c/code\u003e for selecting the most recent reported measurement, and \u003ccode\u003eUnspecified\u003c/code\u003e, which defaults to \u003ccode\u003eLastMeasurement\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eChoosing between \u003ccode\u003eBestMeasurement\u003c/code\u003e and \u003ccode\u003eLastMeasurement\u003c/code\u003e depends on whether the measurements are expected to improve monotonically or if they are significantly noisy, as \u003ccode\u003eBestMeasurement\u003c/code\u003e may be over-optimistic in the latter case.\u003c/p\u003e\n"]]],[],null,[]]
