analiza aiqbench
This arXiv preprint proposes Predictive Coding Dynamics, a residual feedback method that adds prediction-error signals to ODE-RNN and Latent ODE models for sparse, irregularly sampled time series. The reported gains on forecasting and trajectory recovery are claimed by the authors and still need independent replication, and the code is only available via an anonymous link. For ML practitioners working with continuous-time or asynchronous sensor data, the main takeaway is a plug-in mechanism that may improve existing backbones without changing their core architecture.
PCD: Predictive Coding Dynamics for Irregularly Sampled Time Series
arXiv:2610.41506v1 Announce Type: new Abstract: Dynamic systems evolve continuously over time, whereas observations in real scenarios are often sparse, irregular, and asynchronous. Accurate prediction therefore requires inferring latent state evolution between observations, as future values depend on partially observed trajectories. We propose Predictive Coding Dynamics (PCD), a residual feedback mechanism for irregular continuous dynamic models. PCD maintains previous reconstructions, predicts observed entries from them, and incorporates masked signed residuals into state recognition through an energy penalty. The mechanism is implemented with ODE-RNN and Latent ODE, supporting event-based hidden updates and latent state recognition. Experiments on forecasting and trajectory recovery tasks show that PCD improves continuous dynamic backbones under sparse and irregular sampling. The results further indicate that predictive error feedback improves latent state estimation when observations constrain the current trajectory. These results suggest that PCD provides a residual feedback framework that jointly supports trajectory generation, observation consistency checking, and state refinement in continuous-time series modeling. The source code is available at https://anonymous.4open.science/r/PCD-for-paper-92F1/.
Abstract:Dynamic systems evolve continuously over time, whereas observations in real scenarios are often sparse, irregular, and asynchronous. Accurate prediction therefore requires inferring latent state evolution between observations, as future values depend on partially observed trajectories. We propose Predictive Coding Dynamics (PCD), a residual feedback mechanism for irregular continuous dynamic models. PCD maintains previous reconstructions, predicts observed entries from them, and incorporates masked signed residuals into state recognition through an energy penalty. The mechanism is implemented with ODE-RNN and Latent ODE, supporting event-based hidden updates and latent state recognition. Experiments on forecasting and trajectory recovery tasks show that PCD improves continuous dynamic backbones under sparse and irregular sampling. The results further indicate that predictive error feedback improves latent state estimation when observations constrain the current trajectory. These results suggest that PCD provides a residual feedback framework that jointly supports trajectory generation, observation consistency checking, and state refinement in continuous-time series modeling. The source code is available at this https URL.
15 pages. Supplementary material (2 pages) available as an ancillary file
Machine Learning (cs.LG)
arXiv:2610.41506 [cs.LG]
(or arXiv:2610.41506v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.41506 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
PCD_supplement.pdf
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 265 cuvinte
Subiecte conexe
Diagnostic-Guided Longitudinal Modeling for Forecasting Retinal Atrophy Progression
arXiv · 22 sept. 2026
Can Causal Models Enhance Robot Navigation? Online Causal Adaptation for Real-Robot Navigation
arXiv · 16 iun. 2026
Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs
arXiv · 5 oct. 2026
Field Validation of a Multi-Resolution ConvLSTM Framework for Retaining Wall Deformation Prediction
arXiv · 9 iun. 2026