Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift

• URL: http://arxiv.org/abs/2606.02657v1
• Date: Mon, 01 Jun 2026 06:04:42 GMT
• Title: Regime-Arrival Uncertainty in Generalization Bounds under Distribution Shift
• Abstract summary: This paper proposes a framework that generalizes regime-aware models by quantifying the extra risk due to regime composition mismatch.<n>We obtain an exact decomposition, separating regime mismatch from regime sensitivity.<n>The proposed penalty is an ex post realized generalization gap, whereas the training-only estimator does not show significant correlation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The standard generalization bounds assume that the training and deployment distributions are the same, or are static, and don't consider regime switching environments where the ratio of calm vs crisis states is different. This paper proposes a framework that generalizes regime-aware models by quantifying the extra risk due to regime composition mismatch, when distribution shifts are Markov-switching. We obtain an exact decomposition, separating regime mismatch from regime sensitivity; we extend the bound to beta-mixing data using the effective sample size corrected for the spectral gap; and we show a minimax lower bound for synthetic data and on 25 years of global equity indices. The proposed penalty is an ex post realized generalization gap, whereas the training-only estimator does not show significant correlation: the feature geometry of crises can be detected, but not the temporal arrival. Thus, the framework is not a forecast machine. Forecasting the composition of the future regime is an open question in the rare cases of regime change.

Related papers

• Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction [74.05279072166697]
  Exponential-Gaussian Mixture Network (EGMN) models the full conditional WT distribution.<n>EGMN is vulnerable to variance collapse, component redundancy, and inactive components.<n>We propose a Hierarchical Exponential-Gaussian Mixture (HEGM) model that addresses these failure modes.
  arXiv  Detail & Related papers  (2026-08-24T15:06:18Z)
• REGAIN: REconciliation GAIN-driven Auxiliary Direction Learning [12.590383160848141]
  We propose a reconciliation-gain framework that learns normalized auxiliary directions.<n>We show that useful auxiliary directions must provide complementary information about unresolved target uncertainty.<n> Experiments on Beijing PM2.5 and Australian Tourism data show that gain-selected measurements can improve both ordinary multivariate and hierarchical forecasts.
  arXiv  Detail & Related papers  (2026-06-03T02:53:27Z)
• The Need for an External Observer Formalizing the Sufficiency Gap: A Mathematical Extension of Mixture Identifiability and Contextual Grounding in Sequence Models [0.0]
  We construct a binary mixed-regime process with one deterministic textual regime and one random regime governed by an unobserved latent state.<n>The resulting entropy difference is not an ordinary optimization error; it is a sufficiency gap caused by marginalization over an unobserved state.<n>A corrective signal reverses the posterior odds induced by the textual history exactly when its fidelity exceeds the text-only posterior weight assigned to the misleading regime.
  arXiv  Detail & Related papers  (2026-05-26T08:53:11Z)
• DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift [10.952188121974613]
  DeRegiME is a direct multi-horizon probabilistic forecaster.<n>It separates latent uncertainty regimes from the underlying signal.<n>It assigns each forecast location to learned recurring regimes.
  arXiv  Detail & Related papers  (2026-05-19T01:04:21Z)
• Bridging Conformal Prediction and Scenario Optimization: Discarded Constraints and Modular Risk Allocation [0.0]
  This paper revisits that connection directly from a systems-and-control viewpoint.<n>We introduce a simple modular composition rule that combines several blockwise calibration certificates into a single joint guarantee.
  arXiv  Detail & Related papers  (2026-03-19T18:37:58Z)
• A Gentle Introduction to Conformal Time Series Forecasting [0.0]
  This review unifies recent advances in conformal forecasting methods specifically designed to address nonexchangeable data.<n>We first present a theoretical foundation, deriving finite-sample guarantees for split-conformal prediction under mild weak-dependence conditions.<n>We then survey and classify state-of-the-art approaches that mitigate serial dependence by reweighting calibration data, dynamically updating residual distributions, or adaptively tuning target coverage levels in real time.
  arXiv  Detail & Related papers  (2025-11-17T17:12:51Z)
• Bayesian Renormalization [68.8204255655161]
  We present a fully information theoretic approach to renormalization inspired by Bayesian statistical inference. The main insight of Bayesian Renormalization is that the Fisher metric defines a correlation length that plays the role of an emergent RG scale. We provide insight into how the Bayesian Renormalization scheme relates to existing methods for data compression and data generation.
  arXiv  Detail & Related papers  (2023-05-17T18:00:28Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• Dimension Free Generalization Bounds for Non Linear Metric Learning [61.193693608166114]
  We provide uniform generalization bounds for two regimes -- the sparse regime, and a non-sparse regime. We show that by relying on a different, new property of the solutions, it is still possible to provide dimension free generalization guarantees.
  arXiv  Detail & Related papers  (2021-02-07T14:47:00Z)
• Implicit Regularization in ReLU Networks with the Square Loss [56.70360094597169]
  We show that it is impossible to characterize the implicit regularization with the square loss by any explicit function of the model parameters. Our results suggest that a more general framework may be needed to understand implicit regularization for nonlinear predictors.
  arXiv  Detail & Related papers  (2020-12-09T16:48:03Z)
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment [52.02794488304448]
  We propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
  arXiv  Detail & Related papers  (2020-03-26T22:10:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.