Extension to heavier-tailed or misspecified models

Extend the sample-complexity analysis of adaptive multiple testing with e-PS beyond sub-Gaussian log-e-value increments to heavier-tailed or misspecified statistical models.

Background

The paper’s theoretical guarantees broadly cover multiple-testing settings in which the log-e-value increments satisfy sub-Gaussian concentration. The discussion explicitly identifies the extension of this analysis to heavier-tailed observations or misspecified models as unresolved, motivated by the need for reliable inference when the assumed concentration or model structure fails.

References

While our sample-complexity guarantees apply broadly to multiple testing settings with sub-Gaussian log-e-value increments, extending the analysis to heavier-tailed or misspecified models remains an open direction for future work.

— Sample-Efficient Multiple Testing with Adaptive Data Collection  (2609.26651 - Lin et al., 22 Sep 2026) in Section 6, Discussion