cs.LGNov 3, 2026

Decomposing Rank Reversals under Temporal Nonstationarity: Alignment, Aggressiveness, and Instability

Authors: Deying Song, Xueying Ding

Organizations: Carnegie Mellon University, Pittsburgh, PA, USA

Abstract

Under temporal nonstationarity, model performance rankings reverse across training horizons due to heterogeneous sensitivities to memory. While existing literature addresses adaptive lookbacks, effective model complexity, and empirical forecast evaluation in isolation, no unified framework explains the structural mechanics driving these rank reversals. We bridge this gap by deriving a model-agnostic decomposition of out-of-sample R2R^2 into target alignment, miscalibrated aggressiveness, and predictive instability. Within this framework, we mathematically characterize complexity phase boundaries, establish closed-form optimal-memory equations for ridge regression under local drift, and extend these guarantees to complex model architectures via surrogate bounds. We validate these theoretical dynamics by benchmarking 14 linear, tree-based, and neural architectures across large-scale financial panels. In doing so, our framework demonstrates that empirical model rank reversals are driven by predictable surges in miscalibrated aggressiveness, providing a rigorous mechanistic diagnosis of generalization under temporal shift.

Figures & tables

Appendix figures & tables28 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Forecast Collapse in Time-Series Foundation Models

    Aug 14, 2026Shu Wan, Miles Ma, Hank Zhu +4Time Series ForecastingTime-Series Foundation Models

  2. Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift

    Jul 7, 2026Robin Holzinger, Riccardo CollettiDistribution Shift RobustnessNeural Network Generalization

  3. Tracking Adaptation Time: Metrics for Temporal Distribution Shift

    Apr 8, 2026Lorenzo Iovine, Giacomo Ziffer, Emanuele Della ValleDistribution Shift RobustnessTemporal Distribution Shift