AI RESEARCH
Direct Estimation of Schr\"odinger Bridge Time-Series Drifts: Finite-Sample, Asymptotic, and Adaptive Guarantees
arXiv CS.LG
•
ArXi:2605.05432v1 Announce Type: cross We study nonparametric estimation of Schr\"odinger bridge (SB) drifts from i.i.d.\ data observed on a single time interval. Starting from the conditional-ratio form of the Schr\"odinger bridge time-series (SBTS) drift formula, we analyze a direct Nadaraya--Watson plug-in estimator built from kernelized numerator and denominator terms.