Discovering Nonlinear Relations with Minimum Predictive Information Regularization
This work addresses a hard problem in applications requiring causal inference from time series, but appears incremental as it builds on existing deep learning approaches with a new regularization technique.
The paper tackled the problem of identifying directional relations from observational time series with nonlinear interactions by introducing a minimum predictive information regularization method, which substantially outperformed other methods on synthetic datasets and discovered relations in real-world datasets like heart-rate vs. breath-rate.
Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications, yet remains a hard problem. In this work, we introduce a novel minimum predictive information regularization method to infer directional relations from time series, allowing deep learning models to discover nonlinear relations. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets, and discovers the directional relations in a video game environment and a heart-rate vs. breath-rate dataset.