Partial observations of continuous time-series dynamics at arbitrary time stamps exist in many disciplines. Fitting this type of data using statistical models with continuous dynamics is not only promising at an intuitive level but also has practical benefits, including the ability to generate continuous trajectories and to perform inference on previously unseen time stamps. Despite exciting progress in this area, the existing models still face challenges in terms of their representational power and the quality of their variational approximations. We tackle these challenges with continuous latent process flows (CLPF), a principled architecture decoding continuous latent processes into continuous observable processes using a time-dependent normalizing flow driven by a stochastic differential equation. To optimize our model using maximum likelihood, we propose a novel piecewise construction of a variational posterior process and derive the corresponding variational lower bound using trajectory re-weighting. Our ablation studies demonstrate the effectiveness of our contributions in various inference tasks on irregular time grids. Comparisons to state-of-the-art baselines show our model’s favourable performance on both synthetic and real-world time-series data.
Bibtex
@inproceedings{deng21,
title={{Continuous Latent Process Flows}},
author={Ruizhi Deng and Marcus A. Brubaker and Greg Mori and Andreas M. Lehrmann},
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
year={2021}
}
Related Research
-
Self-supervised Learning in Time-Series Forecasting — A Contrastive Learning Approach
Self-supervised Learning in Time-Series Forecasting — A Contrastive Learning Approach
T. Sylvain, L. Meng, and A. Lehrmann.
Research
-
Our NeurIPS 2021 Reading List
Our NeurIPS 2021 Reading List
Y. Cao, K. Y. C. Lui, T. Durand, J. He, P. Xu, N. Mehrasa, A. Radovic, A. Lehrmann, R. Deng, A. Abdi, M. Schlegel, and S. Liu.
Computer Vision; Data Visualization; Graph Representation Learning; Learning And Generalization; Natural Language Processing; Optimization; Reinforcement Learning; Time series Modelling; Unsupervised Learning
Research
-
Agent Forecasting at Flexible Horizons using ODE Flows
Agent Forecasting at Flexible Horizons using ODE Flows
A. Radovic, J. He, J. Ramanan, M. Brubaker, and A. Lehrmann. International Conference on Machine Learning Workshop on Invertible Neural Nets and Normalizing Flows (ICML)
Publications