The paper introduces Internal Dual-Wiener routing (Internal‑DW), a backward‑only method that weight‑balances internal gradient routes in autoregressive forecasting. By estimating bounded Wiener gains for identity and nonlinear paths, it suppresses unpredictable noise while preserving predictable learning signals, reducing forecast error by 5.2%–13.8% on four weak‑drive testbeds compared to full BPTT and outperforming gradient clipping, Jacobian regularization, and truncated BPTT in most cases. The approach shows that long‑horizon supervision can be effective without trusting every backward gradient equally.
arXiv:2607. 29135v1 Announce Type: cross Abstract: Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but this autoregressive rollout feeds every prediction error back as input, so local errors accumulate.
arXiv:2609.08554v1 Announce Type: new Abstract: In data-driven training, multivariate time-series forecasting is usually optimized with a scalar loss averaged over samples, variables, and horizons. T...
RATL is a plug‑in method for multivariate time‑series forecasting that uses a frozen base forecaster to build a memory of its historical forecast residuals. During inference, RATL retrieves residual trajectories from similar past contexts and employs a set‑aware router to combine them, providing learned feedback correction. Experiments demonstrate that this residual‑retrieval approach improves the performance of the base forecaster across various benchmarks and backbones.
arXiv:2608. 07420v1 Announce Type: new Abstract: World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions.
arXiv:2602. 16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima.
arXiv:2609.13840v1 Announce Type: new Abstract: A contract-logistics spare-parts operator is paid on order-level service: an order counts only if every requested line is fulfilled, yet forecasters ar...
The paper introduces a clipped barrier policy gradient method that incorporates a convex regularizer to manage failure risk in budget-constrained operations. By adding a barrier that grows as the budget depletes and clipping rewards below a threshold, the approach ensures that the learned policy maximizes utility while keeping risk within a bounded margin. The authors prove exponential convergence of the training dynamics under convex regularization and demonstrate the method on several benchmark tasks.
arXiv:2610.39902v1 Announce Type: cross Abstract: Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support....
arXiv:2606. 18527v1 Announce Type: cross Abstract: U-calibration studies online forecasting algorithms whose predictions can be consumed by any unknown downstream agent, guaranteeing sublinear regret simultaneously for all proper loss functions.
arXiv:2609.09586v1 Announce Type: new Abstract: Time series foundation models (TSFMs) are increasingly pre-trained on synthetically generated time series trajectories, where the data generating proce...
arXiv:2609.37255v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are pretrained on heterogeneous collections containing billions of observations, yet their training windows are...
arXiv:2608.24593v1 Announce Type: new Abstract: Adaptive optimizers retain gradient history in moment variables, allowing a local change in loss weighting to alter later updates. We examine whether t...