How Does Data Freshness Affect Real-time Supervised Learning?

TL;DR

This paper investigates how data freshness impacts real-time supervised learning performance, revealing non-monotonic effects and proposing new scheduling strategies to optimize inference accuracy based on Age of Information.

Contribution

It introduces a novel analysis of data freshness effects, including non-monotonic behaviors, and develops low-complexity scheduling algorithms using Gittins and Whittle indices for improved real-time inference.

Findings

Prediction error can be non-monotonic with data age.

Proposed scheduling strategies outperform existing methods.

New connection established between Gittins index theory and AoI minimization.

Abstract

In this paper, we analyze the impact of data freshness on real-time supervised learning, where a neural network is trained to infer a time-varying target (e.g., the position of the vehicle in front) based on features (e.g., video frames) observed at a sensing node (e.g., camera or lidar). One might expect that the performance of real-time supervised learning degrades monotonically as the feature becomes stale. Using an information-theoretic analysis, we show that this is true if the feature and target data sequence can be closely approximated as a Markov chain; it is not true if the data sequence is far from Markovian. Hence, the prediction error of real-time supervised learning is a function of the Age of Information (AoI), where the function could be non-monotonic. Several experiments are conducted to illustrate the monotonic and non-monotonic behaviors of the prediction error. To minimize the inference error in real-time, we propose a new "selection-from-buffer" model for sending the features, which is more general than the "generate-at-will" model used in earlier studies. By using Gittins and Whittle indices, low-complexity scheduling strategies are developed to minimize the inference error, where a new connection between the Gittins index theory and Age of Information (AoI) minimization is discovered. These scheduling results hold (i) for minimizing general AoI functions (monotonic or non-monotonic) and (ii) for general feature transmission time distributions. Data-driven evaluations are presented to illustrate the benefits of the proposed scheduling algorithms.