Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates

• URL: http://arxiv.org/abs/2607.05452v1
• Date: Sun, 05 Jul 2026 15:59:15 GMT
• Title: Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
• Abstract summary: We study whether robustness requires specialized architectures, or whether it can be obtained through a simple training intervention.<n>Across electricity-price forecasting, reservoir hydrology, and meteorology, our method substantially improves robustness under Gaussian noise.<n>It yields the most robust model in our experiments, outperforming a deliberately strong bounded architectural foil.
• Score: 2.6904447021876297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series forecasters that use exogenous covariates are fragile in deployment: when those covariates are noised, temporally misaligned, or missing, strong exogenous-fusion and exogenous-adapted models can degrade far above the endogenous-only floor. We study whether such robustness requires specialized architectures, or whether it can be obtained through a simple training intervention. We propose exogenous dropout, a model-agnostic method that randomly zeros whole exogenous channels during training. Across electricity-price forecasting, reservoir hydrology, and meteorology, exogenous dropout substantially improves robustness under Gaussian noise, temporal misalignment, and fully missing channels, while preserving clean accuracy. Applied to a dual-correlation network, it yields the most robust model in our experiments, outperforming a deliberately strong bounded architectural foil, BoundEx, which combines a learnable gate, a fallback residual to the endogenous backbone, and per-channel exogenous FiLM modulation. Architecture-by-dropout ablations, gate-behavior diagnostics, and a representation-level bound show that explicit architectural boundedness is not necessary for this robustness: an unbounded model trained with exogenous dropout is more robust than the bounded model in every domain. We release a corruption-robustness benchmark and recommend exogenous dropout as a simple, strong baseline for future work on time series forecasting with covariates.

Related papers

• RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs [31.6943694848236]
  RainODE is a framework that models precipitation evolution in latent space using a Neural ODE.<n>This formulation enables derivative-consistent temporal dynamics and captures the dominant large-scale advective motion of precipitation systems.<n>A source modeling module based on a Brownian Bridge restores residual intensity variations while preserving fine-grained structures.
  arXiv  Detail & Related papers  (2026-06-29T06:48:02Z)
• On the Redundancy of Timestep Embeddings in Diffusion Models [3.0458514384586404]
  Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales.<n>We provide a theoretical framework demonstrating that, under certain conditions, the global minimizer of the diffusion training objective can be achieved without explicit timestep conditioning.<n>Our analysis suggests these architectures can implicitly infer noise scales from the corrupted input under specific assumptions, rendering explicit temporal conditioning redundant.
  arXiv  Detail & Related papers  (2026-06-18T16:01:39Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Improving Spatio-Temporal Residual Error Propagation by Mitigating Over-Squashing [4.62541204592513]
  We introduce Teger, a structured uncertainty module that overcomes the spa- tial and temporal limitations of error-related autoregressive forecasting.<n>Teger is backbone-agnostic, requiring only the latent state produced by any autoregressive encoder.
  arXiv  Detail & Related papers  (2026-05-18T08:51:33Z)
• PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting [62.22445401483844]
  Existing methods are severely constrained by the bottleneck of compounding errors.<n>We propose a universal framework called -Cast-Corrector (Plug-and-Play Corrector)<n>Our method significantly enhances the long-term stability of coupled forecasting systems.
  arXiv  Detail & Related papers  (2026-05-09T13:12:33Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• WADEPre: A Wavelet-based Decomposition Model for Extreme Precipitation Nowcasting with Multi-Scale Learning [10.39382090254482]
  WADEPre is a wavelet-based decomposition model for extreme precipitation that transitions the modeling into the wavelet domain.<n> Experiments on the SEVIR and Shanghai Radar datasets demonstrate that WADEPre achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T13:40:57Z)
• From Snow to Rain: Evaluating Robustness, Calibration, and Complexity of Model-Based Robust Training [5.284812806199192]
  We study a family of model-based training approaches that leverage a learned nuisance variation model to generate realistic corruptions.<n>New hybrid strategies that combine random coverage with adversarial refinement in nuisance space are studied.
  arXiv  Detail & Related papers  (2026-01-14T04:49:44Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Restoration Score Distillation: From Corrupted Diffusion Pretraining to One-Step High-Quality Generation [82.39763984380625]
  We propose textitRestoration Score Distillation (RSD), a principled generalization of Denoising Score Distillation (DSD)<n>RSD accommodates a broader range of corruption types, such as blurred, incomplete, or low-resolution images.<n>It consistently surpasses its teacher model across diverse restoration tasks on both natural and scientific datasets.
  arXiv  Detail & Related papers  (2025-05-19T17:21:03Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)

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.