Adaptive prediction theory combining offline and online learning

arXiv:2512.00342v2 Announce Type: replace Abstract: Real-world intelligence systems usually operate by combining offline learning and online adaptation with highly correlated and non-stationary system data or signals, which, however, has rarely been investigated theoretically in the literature. This paper initiates a theoretical investigation on the prediction performance of a two-stage learning framework combining offline and online algorithms for a class of nonlinear stochastic dynamical systems. For the offline-learning phase, we establish an upper bound on the generalization error for approximate nonlinear-least-squares estimation under general datasets with strong correlation and distribution shift, leveraging the Kullback-Leibler divergence to quantify the distributional discrepancies. For the online-adaptation phase, we address, on the basis of the offline-trained model, the possible uncertain parameter drift in real-world target systems by proposing a meta-LMS prediction algorithm. This two-stage framework, integrating offline learning with online adaptation, demonstrates superior prediction performances compared with either purely offline or online methods. Both theoretical guarantees and empirical studies are provided.

Related

• BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous control
• FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
• Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection
• Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification

Source: arXiv cs.LG | 2026-08-26