Learning and Communications Co-Design for Remote Inference Systems: Feature Length Selection and Transmission Scheduling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shisher, Md Kamran Chowdhury, Ji, Bo, Hou, I-Hong, Sun, Yin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929396021985280
author Shisher, Md Kamran Chowdhury
Ji, Bo
Hou, I-Hong
Sun, Yin
author_facet Shisher, Md Kamran Chowdhury
Ji, Bo
Hou, I-Hong
Sun, Yin
contents In this paper, we consider a remote inference system, where a neural network is used to infer a time-varying target (e.g., robot movement), based on features (e.g., video clips) that are progressively received from a sensing node (e.g., a camera). Each feature is a temporal sequence of sensory data. The inference error is determined by (i) the timeliness and (ii) the sequence length of the feature, where we use Age of Information (AoI) as a metric for timeliness. While a longer feature can typically provide better inference performance, it often requires more channel resources for sending the feature. To minimize the time-averaged inference error, we study a learning and communication co-design problem that jointly optimizes feature length selection and transmission scheduling. When there is a single sensor-predictor pair and a single channel, we develop low-complexity optimal co-designs for both the cases of time-invariant and time-variant feature length. When there are multiple sensor-predictor pairs and multiple channels, the co-design problem becomes a restless multi-arm multi-action bandit problem that is PSPACE-hard. For this setting, we design a low-complexity algorithm to solve the problem. Trace-driven evaluations demonstrate the potential of these co-designs to reduce inference error by up to 10000 times.
format Preprint
id arxiv_https___arxiv_org_abs_2308_10094
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning and Communications Co-Design for Remote Inference Systems: Feature Length Selection and Transmission Scheduling
Shisher, Md Kamran Chowdhury
Ji, Bo
Hou, I-Hong
Sun, Yin
Information Theory
Networking and Internet Architecture
In this paper, we consider a remote inference system, where a neural network is used to infer a time-varying target (e.g., robot movement), based on features (e.g., video clips) that are progressively received from a sensing node (e.g., a camera). Each feature is a temporal sequence of sensory data. The inference error is determined by (i) the timeliness and (ii) the sequence length of the feature, where we use Age of Information (AoI) as a metric for timeliness. While a longer feature can typically provide better inference performance, it often requires more channel resources for sending the feature. To minimize the time-averaged inference error, we study a learning and communication co-design problem that jointly optimizes feature length selection and transmission scheduling. When there is a single sensor-predictor pair and a single channel, we develop low-complexity optimal co-designs for both the cases of time-invariant and time-variant feature length. When there are multiple sensor-predictor pairs and multiple channels, the co-design problem becomes a restless multi-arm multi-action bandit problem that is PSPACE-hard. For this setting, we design a low-complexity algorithm to solve the problem. Trace-driven evaluations demonstrate the potential of these co-designs to reduce inference error by up to 10000 times.
title Learning and Communications Co-Design for Remote Inference Systems: Feature Length Selection and Transmission Scheduling
topic Information Theory
Networking and Internet Architecture
url https://arxiv.org/abs/2308.10094