Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models
This addresses a domain-specific problem in sequential prediction tasks, such as those in machine learning or AI, by improving model performance through temporal abstraction, though it appears incremental as it builds on existing recurrent dynamics models.
The paper tackles the problem of enabling recurrent dynamics models to be temporally abstract by introducing Adaptive Skip Intervals (ASI), a method that allows models to choose their own prediction sampling rate, resulting in gains in computational efficiency and prediction accuracy for certain tasks.
We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective. Moreover, in many situations, there exist prediction intervals which result in particularly easy-to-predict transitions. We show that there are prediction tasks for which we gain both computational efficiency and prediction accuracy by allowing the model to make predictions at a sampling rate which it can choose itself.