Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models

TL;DR

This paper presents Adaptive Skip Intervals (ASI), a method enabling recurrent models to choose their own temporal sampling rate, improving efficiency and accuracy in sequential prediction tasks by focusing on predictable transitions.

Contribution

The paper introduces ASI, a novel approach allowing models to adaptively select prediction intervals, enhancing temporal abstraction in recurrent dynamical models.

Findings

ASI improves computational efficiency in sequential prediction.

ASI increases prediction accuracy by focusing on easy-to-predict transitions.

Adaptive sampling leads to better performance in tasks with variable event timing.

Abstract

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.