Mean-Square Deviation of the Empirical Average of a Bounded Borel Function under a Tensor Power
lemmaAnalysisProbabilitylem:empirical-average-variance-euclidean-2026aUnder the N-fold tensor power of a probability measure rho, the integral of a bounded Borel function phi against the empirical measure has mean-square deviation (int d rho - (int phi d from its mean, which is at most (int d rho)/N.
In the setting of Wasserstein Spaces, Random Vectors, Vector Fields and Symmetric Matrices in Every Dimension: Standing Notation, whose probability space is not used, let , let with tensor power , let , , be the block maps of Particle Blocks of the Configuration Space: Block Maps, Configurations, Product Maps and Diagonal Points §blocks, and let be the empirical measure of . In real arithmetic stands for its image under the canonical map, which is positive by claim 3 of Properties of the Canonical Map from the Natural Numbers to an Ordered Field, and means . Let be bounded and Borel, let denote its pointwise square, which is Borel by claim 3 of Arithmetic, Absolute Values, and Pointwise Limits of Measurable Real-Valued Functions and bounded by the square of a bound for , and put
integrals of bounded Borel functions as in Probability Measures on Euclidean Space and Random Vectors: Standing Notation §measures. Then the following hold.
1. (The empirical average)¶ For every the function is integrable with respect to , and
The function , , is Borel and bounded.
2. (Mean-square deviation)¶
Loading…
Prerequisites
No prerequisites tracked.
Dependents
No dependents yet.
Dependent proofs
No dependent proofs yet.
No relations recorded yet.