# Timely Communications for Remote Inference

arXiv: https://arxiv.org/abs/2404.16281 · HTML: https://mlsanity.com/paper/2404.16281/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 73 references that are in the map.
- First posted on arXiv 25 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Stochastic Adversarial Video Prediction](https://mlsanity.com/paper/1804.01523/) (2018)
- [Self-Supervised Visual Planning with Temporal Skip Connections](https://mlsanity.com/paper/1710.05268/) (2017)
- [Age of Information: An Introduction and Survey](https://mlsanity.com/paper/2007.08564/) (2020)
- [A Minimax Approach to Supervised Learning](https://mlsanity.com/paper/1606.02206/) (2016)
- [Scheduling Policies for Minimizing Age of Information in Broadcast Wireless Networks](https://mlsanity.com/paper/1801.01803/) (2018)
- [Age of Information: Whittle Index for Scheduling Stochastic Arrivals](https://mlsanity.com/paper/1801.03422/) (2018)
- [A Whittle Index Approach to Minimizing Functions of Age of Information](https://mlsanity.com/paper/1908.10438/) (2019)
- [On Universal Features for High-Dimensional Learning and Inference](https://mlsanity.com/paper/1911.09105/) (2019)
- [Sampling for Data Freshness Optimization: Non-linear Age Functions](https://mlsanity.com/paper/1812.07241/) (2018)
- [The Age of Correlated Features in Supervised Learning based Forecasting](https://mlsanity.com/paper/2103.00092/) (2021)
- [Closed-Form Whittle's Index-Enabled Random Access for Timely Status Update](https://mlsanity.com/paper/1910.13871/) (2019)
- [How Does Data Freshness Affect Real-time Supervised Learning?](https://mlsanity.com/paper/2208.06948/) (2022)
- [A Local Geometric Interpretation of Feature Extraction in Deep Feedforward Neural Networks](https://mlsanity.com/paper/2202.04632/) (2022)
- [Learning and Communications Co-Design for Remote Inference Systems: Feature Length Selection and Transmission Scheduling](https://mlsanity.com/paper/2308.10094/) (2023)
- [On the Monotonicity of Information Aging](https://mlsanity.com/paper/2403.03380/) (2024)
- [Age-Optimal Multi-Flow Status Updating with Errors: A Sample-Path Approach](https://mlsanity.com/paper/2310.00243/) (2023)

## Built on by (most cited first, 6 of 6)

- [Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization](https://mlsanity.com/paper/2501.02521/) (2025)
- [Online Learning of Whittle Indices for Restless Bandits with Non-Stationary Transition Kernels](https://mlsanity.com/paper/2506.18186/) (2025)
- [Multimodal Remote Inference](https://mlsanity.com/paper/2508.07555/) (2025)
- [Efficient Information Updates in Compute-First Networking via Reinforcement Learning with Joint AoI and VoI](https://mlsanity.com/paper/2505.06025/) (2025)
- [Monitoring State Transitions in Markovian Systems with Sampling Cost](https://mlsanity.com/paper/2510.22327/) (2025)
- [Joint Optimization of Training and Inference in Federated Edge Learning via Constrained Multi-Objective Deep Reinforcement Learning](https://mlsanity.com/paper/2605.25916/) (2026)

## Abstract (arXiv)

In this paper, we analyze the impact of data freshness on remote inference systems, where a pre-trained neural network blue infers a time-varying target (e.g., the locations of vehicles and pedestrians) based on features (e.g., video frames) observed at a sensing node (e.g., a camera). One might expect that the performance of a remote inference system 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, whereas it is not true if the data sequence is far from being Markovian. Hence, the inference error is a function of Age of Information (AoI), where the function could be non-monotonic. 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. In addition, we design low-complexity scheduling policies to improve inference performance. For single-source, single-channel systems, we provide an optimal scheduling policy. In multi-source, multi-channel systems, the scheduling problem becomes a multi-action restless multi-armed bandit problem. For this setting, we design a new scheduling policy by integrating Whittle index-based source selection and duality-based feature selection-from-buffer algorithms. This new scheduling policy is proven to be asymptotically optimal. These scheduling results hold for minimizing general AoI functions (monotonic or non-monotonic). Data-driven evaluations demonstrate the significant advantages of our proposed scheduling policies.