Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2110.06257 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910987561467904 |
|---|---|
| author | Balsells-Rodas, Carles Sumba, Xavier Narendra, Tanmayee Tu, Ruibo Schweikert, Gabriele Kjellstrom, Hedvig Li, Yingzhen |
| author_facet | Balsells-Rodas, Carles Sumba, Xavier Narendra, Tanmayee Tu, Ruibo Schweikert, Gabriele Kjellstrom, Hedvig Li, Yingzhen |
| contents | Causal discovery, i.e., inferring underlying causal relationships from observational data, is highly challenging for AI systems. In a time series modeling context, traditional causal discovery methods mainly consider constrained scenarios with fully observed variables and/or data from stationary time-series. We develop a causal discovery approach to handle a wide class of nonstationary time series that are conditionally stationary, where the nonstationary behaviour is modeled as stationarity conditioned on a set of latent state variables. Named State-Dependent Causal Inference (SDCI), our approach is able to recover the underlying causal dependencies, with provable identifiablity for the state-dependent causal structures. Empirical experiments on nonlinear particle interaction data and gene regulatory networks demonstrate SDCI's superior performance over baseline causal discovery methods. Improved results over non-causal RNNs on modeling NBA player movements demonstrate the potential of our method and motivate the use of causality-driven methods for forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2110_06257 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Causal Discovery from Conditionally Stationary Time Series Balsells-Rodas, Carles Sumba, Xavier Narendra, Tanmayee Tu, Ruibo Schweikert, Gabriele Kjellstrom, Hedvig Li, Yingzhen Machine Learning Causal discovery, i.e., inferring underlying causal relationships from observational data, is highly challenging for AI systems. In a time series modeling context, traditional causal discovery methods mainly consider constrained scenarios with fully observed variables and/or data from stationary time-series. We develop a causal discovery approach to handle a wide class of nonstationary time series that are conditionally stationary, where the nonstationary behaviour is modeled as stationarity conditioned on a set of latent state variables. Named State-Dependent Causal Inference (SDCI), our approach is able to recover the underlying causal dependencies, with provable identifiablity for the state-dependent causal structures. Empirical experiments on nonlinear particle interaction data and gene regulatory networks demonstrate SDCI's superior performance over baseline causal discovery methods. Improved results over non-causal RNNs on modeling NBA player movements demonstrate the potential of our method and motivate the use of causality-driven methods for forecasting. |
| title | Causal Discovery from Conditionally Stationary Time Series |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2110.06257 |