To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series

• URL: http://arxiv.org/abs/2601.23114v2
• Date: Mon, 02 Feb 2026 17:05:48 GMT
• Title: To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series
• Authors: Jiaming Ma, Siyuan Mu, Ruilin Tang, Haofeng Ma, Qihe Huang, Zhengyang Zhou, Pengkun Wang, Binwu Wang, Yang Wang,
• Abstract summary: The prevailing Direct Forecasting (DF) paradigm dominates Long-term Time Series Forecasting (LTSF) by forcing models to predict the entire future horizon in a single forward pass.<n>In this work, we uncover a counter-intuitive optimization anomaly: models trained on short horizons-when coupled with our proposed Evolutionary Forecasting (EF) paradigm-significantly outperform those trained directly on long horizons.
• Score: 27.499122225390092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The prevailing Direct Forecasting (DF) paradigm dominates Long-term Time Series Forecasting (LTSF) by forcing models to predict the entire future horizon in a single forward pass. While efficient, this rigid coupling of output and evaluation horizons necessitates computationally prohibitive re-training for every target horizon. In this work, we uncover a counter-intuitive optimization anomaly: models trained on short horizons-when coupled with our proposed Evolutionary Forecasting (EF) paradigm-significantly outperform those trained directly on long horizons. We attribute this success to the mitigation of a fundamental optimization pathology inherent in DF, where conflicting gradients from distant futures cripple the learning of local dynamics. We establish EF as a unified generative framework, proving that DF is merely a degenerate special case of EF. Extensive experiments demonstrate that a singular EF model surpasses task-specific DF ensembles across standard benchmarks and exhibits robust asymptotic stability in extreme extrapolation. This work propels a paradigm shift in LTSF: moving from passive Static Mapping to autonomous Evolutionary Reasoning.

Related papers

• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs [22.486083545585984]
  Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting.<n>Existing approaches typically employ a naive autoregressive generation strategy.<n>We propose textbfF-LLM, a novel closed-loop framework.
  arXiv  Detail & Related papers  (2026-02-13T09:35:12Z)
• From Observations to States: Latent Time Series Forecasting [65.98504021691666]
  We propose Latent Time Series Forecasting (LatentTSF), a novel paradigm that shifts TSF from observation regression to latent state prediction.<n>Specifically, LatentTSF employs an AutoEncoder to project observations at each time step into a higher-dimensional latent state space.<n>Our proposed latent objectives implicitly maximize mutual information between predicted latent states and ground-truth states and observations.
  arXiv  Detail & Related papers  (2026-01-30T20:39:44Z)
• Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving [54.46325690390831]
  We propose Model-based Policy Adaptation (MPA), a general framework that enhances the robustness and safety of pretrained E2E driving agents during deployment.<n>MPA first generates diverse counterfactual trajectories using a geometry-consistent simulation engine.<n>MPA trains a diffusion-based policy adapter to refine the base policy's predictions and a multi-step Q value model to evaluate long-term outcomes.
  arXiv  Detail & Related papers  (2025-11-26T17:01:41Z)
• SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting [8.141505251306622]
  Diffusion models have recently shown promise in time series forecasting.<n>They often fail to achieve state-of-the-art point estimation performance.<n>We propose SimDiff, a single-stage, end-to-end framework for point estimation.
  arXiv  Detail & Related papers  (2025-11-24T16:09:55Z)
• Optimal Look-back Horizon for Time Series Forecasting in Federated Learning [26.070107882914844]
  This paper presents a principled framework for adaptive horizon selection in federated time series forecasting.<n>We derive a decomposition of the forecasting loss into a Bayesian term, which reflects irreducible uncertainty.<n>We prove that the total forecasting loss is minimized at the smallest horizon where the irreducible loss starts to saturate, while the approximation loss continues to rise.
  arXiv  Detail & Related papers  (2025-11-16T21:46:54Z)
• Operator Flow Matching for Timeseries Forecasting [2.406359246841227]
  Existing autoregressive and diffusion-based approaches often suffer cumulative errors and discretisation artifacts that limit long, physically consistent forecasts.<n>We prove an upper bound on FNO error and propose TempO, a latent flow matching model leveraging sparse conditioning with channel folding.
  arXiv  Detail & Related papers  (2025-10-16T19:40:56Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching [9.465542901469815]
  Conditional Guided Flow Matching (CGFM) is a model-agnostic framework that extends flow matching by integrating outputs from an auxiliary predictive model.<n>CGFM incorporates historical data as both conditions and guidance, uses two-sided conditional paths, and employs affine paths to expand the path space.<n> Experiments across datasets and baselines show CGFM consistently outperforms state-of-the-art models, advancing forecasting.
  arXiv  Detail & Related papers  (2025-07-09T18:03:31Z)
• Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting [52.6508222408558]
  We introduce Elucidated Rolling Diffusion Models (ERDM)<n>ERDM is the first framework to unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM)<n>On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5circ resolution, ERDM consistently outperforms key diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-06-24T21:44:31Z)
• On conditional diffusion models for PDE simulations [53.01911265639582]
  We study score-based diffusion models for forecasting and assimilation of sparse observations. We propose an autoregressive sampling approach that significantly improves performance in forecasting. We also propose a new training strategy for conditional score-based models that achieves stable performance over a range of history lengths.
  arXiv  Detail & Related papers  (2024-10-21T18:31:04Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• FreDF: Learning to Forecast in the Frequency Domain [54.2091536822376]
  Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences.<n>We propose the Frequency-enhanced Direct Forecast (FreDF) which mitigates label autocorrelation by learning to forecast in the frequency domain.
  arXiv  Detail & Related papers  (2024-02-04T08:23:41Z)

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.