arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.12652cs.LGcs.AIeess.SP
收藏

约束后验采样:带硬约束的时间序列生成

Constrained Posterior Sampling: Time Series Generation with Hard Constraints

Department of Electrical and Computer Engineering, The University of Texas at Austin(电气与计算机工程系,德克萨斯大学奥斯汀分校)

Sai Shankar Narasimhan, Shubhankar Agarwal, Litu Rout, Sanjay Shakkottai, Sandeep P. Chinchali

AI总结:

针对现有约束时间序列生成方法可扩展性差、样本质量低的问题,提出基于扩散的约束后验采样算法CPS,无需额外训练即可支持约百个约束,在多类真实数据集上样本质量和相似性显著优于SOTA方法。

摘要:

生成逼真的时间序列样本对于模型压力测试以及通过合成数据保护用户隐私至关重要。在工程和安全关键应用中,这些样本必须满足特定的硬约束,这类约束要么是领域特定的,要么是由物理或自然规律天然施加的。例如,生成带有峰值需求时间约束的电力需求模式,可用于压力测试恶劣天气条件下电网的运行情况。现有的约束时间序列生成方法要么不可扩展,要么会降低样本质量。为解决这些挑战,我们提出了约束后验采样(Constrained Posterior Sampling,CPS),这是一种基于扩散的采样算法,旨在每次去噪更新后将后验均值估计投影到约束集中。值得注意的是,CPS可扩展至约100个大量约束,且无需额外训练。我们提供了理论依据,阐明了投影步骤对采样的影响。实验结果表明,在真实世界的股票、交通和空气质量数据集上,CPS在样本质量和与真实时间序列的相似性方面分别优于当前最优方法约70%和22%。

英文摘要:

Generating realistic time series samples is crucial for stress-testing models and protecting user privacy by using synthetic data. In engineering and safety-critical applications, these samples must meet certain hard constraints that are domain-specific or naturally imposed by physics or nature. Consider, for example, generating electricity demand patterns with constraints on peak demand times. This can be used to stress-test the functioning of power grids during adverse weather conditions. Existing approaches for generating constrained time series are either not scalable or degrade sample quality. To address these challenges, we introduce Constrained Posterior Sampling (CPS), a diffusion-based sampling algorithm that aims to project the posterior mean estimate into the constraint set after each denoising update. Notably, CPS scales to a large number of constraints ($\sim100$) without requiring additional training. We provide theoretical justifications highlighting the impact of our projection step on sampling. Empirically, CPS outperforms state-of-the-art methods in sample quality and similarity to real time series by around 70\% and 22\%, respectively, on real-world stocks, traffic, and air quality datasets.

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。

↑