Locate the RFF-MMD and SWD power transition

Determine the power transition between detectable and undetectable drift for distributed RFF-MMD and Sliced Wasserstein Distance by conducting an intensity-grid power analysis with repeated random seeds across realized-flip fractions between the weak and strong regimes.

Background

The Trendyol experiments identify a strong regime in which RFF-MMD and SWD can track injected drift and a weak regime, with realized-flip fractions of 0.29–0.57%, in which neither method reliably discriminates drift from the null baseline. These two regimes bracket a failure and a success region but do not identify the intermediate power transition. The authors explicitly propose an intensity-grid study with repeated seeds to determine whether the observed floor reflects a fundamental sensitivity limit or configuration-dependent threshold effects.

References

The two regimes thus bracket a failure and a success region without locating the power transition between them; an intensity-grid power analysis (e.g.\ {0.5, 1, 2, 3, 5, 7.5, 10}\% with repeated seeds) is left to future work, and the weak-regime results mark an empirical failure point for this configuration rather than a fundamental sensitivity bound.

— Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations  (2610.08132 - Pullu et al., 6 Oct 2026) in Section 6.3.4, Performance by drift type and severity regime

Fourth, every detector has a floor. At realized-flip fractions of 0.29--0.57\%, neither RFF-MMD nor SWD separates drift from the null baseline; whether this is a fundamental sensitivity bound or a threshold that shifts with sample size and kernel choice requires intensity-grid power analysis with repeated seeds.

— Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations  (2610.08132 - Pullu et al., 6 Oct 2026) in Section 8, Conclusion