Continuous Time Evidential Distributions for Irregular Time Series
This addresses prediction problems in domains like healthcare where data is irregular, though it appears incremental as it builds on existing uncertainty methods for time series.
The paper tackles the challenge of making predictions from irregular time series, where observations are sporadic, by introducing EDICT, a method that learns an evidential distribution in continuous time to characterize uncertainty. The result shows that EDICT achieves competitive performance on time series classification tasks and enables uncertainty-guided inference with noisy data.
Prevalent in many real-world settings such as healthcare, irregular time series are challenging to formulate predictions from. It is difficult to infer the value of a feature at any given time when observations are sporadic, as it could take on a range of values depending on when it was last observed. To characterize this uncertainty we present EDICT, a strategy that learns an evidential distribution over irregular time series in continuous time. This distribution enables well-calibrated and flexible inference of partially observed features at any time of interest, while expanding uncertainty temporally for sparse, irregular observations. We demonstrate that EDICT attains competitive performance on challenging time series classification tasks and enabling uncertainty-guided inference when encountering noisy data.