arXiv cs.AI· Matteo Rufolo, Dario Piga, Filippo Pura, Marco Forgione·· 6 天前AI 评分22
面向系统辨识的上下文学习：概率化建模、长序列处理与基准验证
In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation
AI 导读
该研究将上下文学习用于系统辨识，提出统一的概率化元辨识架构，结合 Transformer 编码器-解码器与长训练序列处理机制，实现长时程校准预测。预训练元模型还可作为不确定性感知的合成数据生成器，在真实数据稀缺时为正则化参数模型提供任务特定数据。在标准非线性系统辨识基准及分布外场景中，该方法精度与 SOTA 方法相当，并展现出强泛化能力，仅靠输入适配即可应对显著分布偏移。
正文 · 原文
Abstract:Traditional system identification typically involves two steps: initially, training data is processed to estimate a model of the system of interest; then, the model is used to predict outputs for new input queries. In contrast, recent in-context learning approaches learn a meta model that maps directly from training data and query inputs to outputs in a zero-shot fashion, bypassing explicit model estimation. This approach leverages a meta model trained offline, on large sets of synthetically generated data, to emulate the behavior of a system identification algorithm. In this work, we advance this meta-learning framework for system identification in three directions. First, we develop a unified probabilistic meta-identification architecture that combines a Transformer-based encoder-decoder with tailored mechanisms for handling long training sequences, enabling calibrated predictions over long horizons. Second, we show how a pre-trained meta model can act as an uncertainty-aware synthetic data generator for classical system identification, providing task-specific data that regularize parametric models when real data are scarce. Third, we systematically evaluate the framework on standard nonlinear system identification benchmarks and on a challenging out-of-distribution scenario, demonstrating competitive accuracy with state-of-the-art methods and strong generalization, including cases where input-only adaptation is sufficient to handle significant distribution shifts.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY) |
| Cite as: | arXiv:2610.13411 [cs.LG] |
| (or arXiv:2610.13411v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13411 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Matteo Rufolo [view email]
[v1]
Fri, 9 Oct 2026 11:21:14 UTC (2,385 KB)
来源：arXiv cs.AI · arxiv.org