自监督学习可识别复杂系统的潜在动态规律
Self-supervised contrastive learning performs non-linear system identification
- 提出动态对比学习框架，从观测数据中解耦非线性系统动态
- 理论证明在非线性观测下仍能准确识别线性、切换线性与非线性动态
- 适用于时序数据建模，适合研究动态系统建模的研究者
自监督学习（SSL）在多个任务和领域取得了显著成功。有观点认为，其成功源于与可识别表征学习的关联：时间结构和辅助变量确保潜在表征与数据的真实生成因素相关。本文深化这一联系，表明自监督学习可在潜在空间中实现系统识别。我们提出动态对比学习框架，在非线性观测模型下，能够揭示线性、切换线性及非线性动态，并提供理论保证，通过实验证实其有效性。
原文摘要 · Abstract (English)
Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal structure and auxiliary variables ensure that latent representations are related to the true underlying generative factors of the data. Here, we deepen this connection and show that SSL can perform system identification in latent space. We propose dynamics contrastive learning, a framework to uncover linear, switching linear and non-linear dynamics under a non-linear observation model, give theoretical guarantees and validate them empirically.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。