Salvato in:
Dettagli Bibliografici
Autori principali: LU, Echo Diyun, Findling, Charles, Clausel, Marianne, Leite, Alessandro, Gong, Wei, Kersaudy, Pierric
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.03298
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915778930933760
author LU, Echo Diyun
Findling, Charles
Clausel, Marianne
Leite, Alessandro
Gong, Wei
Kersaudy, Pierric
author_facet LU, Echo Diyun
Findling, Charles
Clausel, Marianne
Leite, Alessandro
Gong, Wei
Kersaudy, Pierric
contents Regime transitions routinely break stationarity in time series, making calibrated uncertainty as important as point accuracy. We study distribution-free uncertainty for regime-switching forecasting by coupling Deep Switching State Space Models with Adaptive Conformal Inference (ACI) and its aggregated variant (AgACI). We also introduce a unified conformal wrapper that sits atop strong sequence baselines including S4, MC-Dropout GRU, sparse Gaussian processes, and a change-point local model to produce online predictive bands with finite-sample marginal guarantees under nonstationarity and model misspecification. Across synthetic and real datasets, conformalized forecasters achieve near-nominal coverage with competitive accuracy and generally improved band efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction
LU, Echo Diyun
Findling, Charles
Clausel, Marianne
Leite, Alessandro
Gong, Wei
Kersaudy, Pierric
Machine Learning
Artificial Intelligence
Regime transitions routinely break stationarity in time series, making calibrated uncertainty as important as point accuracy. We study distribution-free uncertainty for regime-switching forecasting by coupling Deep Switching State Space Models with Adaptive Conformal Inference (ACI) and its aggregated variant (AgACI). We also introduce a unified conformal wrapper that sits atop strong sequence baselines including S4, MC-Dropout GRU, sparse Gaussian processes, and a change-point local model to produce online predictive bands with finite-sample marginal guarantees under nonstationarity and model misspecification. Across synthetic and real datasets, conformalized forecasters achieve near-nominal coverage with competitive accuracy and generally improved band efficiency.
title Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.03298