自监督对比学习执行非线性系统辨识
Self-supervised contrastive learning performs non-linear system identification
AI总结：
本文深化了自监督学习与可辨识表示学习的联系，提出dynamics contrastive learning框架，在非线性观测模型下执行潜在空间的系统辨识，揭示线性和非线性动力学，并提供理论保证与实验验证。
摘要：
自监督学习（SSL）方法在许多任务和领域取得了巨大成功。有人认为这些成功归因于SSL与可辨识表示学习之间的联系：时间结构和辅助变量确保了潜在表示与数据的真实底层生成因子相关。在此，我们深化了这一联系，并表明SSL能在潜在空间中执行系统辨识。我们提出了dynamics contrastive learning框架，用于在非线性观测模型下揭示线性、切换线性和非线性动力学，提供了理论保证并进行了实验验证。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
