# Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learning

arXiv: https://arxiv.org/abs/2305.08169 · HTML: https://mlsanity.com/paper/2305.08169/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 14 May 2023.

## Builds on (most cited first, 9 of 9)

- [On Kernelized Multi-armed Bandits](https://mlsanity.com/paper/1704.00445/) (2017)
- [Learning-based Model Predictive Control for Safe Exploration](https://mlsanity.com/paper/1803.08287/) (2018)
- [Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control](https://mlsanity.com/paper/1906.01376/) (2019)
- [Feedback Linearization based on Gaussian Processes with event-triggered Online Learning](https://mlsanity.com/paper/1911.06565/) (2019)
- [Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processes](https://mlsanity.com/paper/2010.05818/) (2020)
- [Control Barriers in Bayesian Learning of System Dynamics](https://mlsanity.com/paper/2012.14964/) (2020)
- [Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications](https://mlsanity.com/paper/2109.02606/) (2021)
- [Event-triggered Learning for Resource-efficient Networked Control](https://mlsanity.com/paper/1803.01802/) (2018)
- [Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions](https://mlsanity.com/paper/2208.10733/) (2022)

## Built on by (most cited first, 8 of 8)

- [Cooperative Learning with Gaussian Processes for Euler-Lagrange Systems Tracking Control under Switching Topologies](https://mlsanity.com/paper/2402.03048/) (2024)
- [Streaming Generated Gaussian Process Experts for Online Learning and Control: Extended Version](https://mlsanity.com/paper/2508.03679/) (2025)
- [Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy](https://mlsanity.com/paper/2307.13945/) (2023)
- [Quality or Quantity? Error-Informed Selective Online Learning with Gaussian Processes in Multi-Agent Systems: Extended Version](https://mlsanity.com/paper/2601.14275/) (2026)
- [Decentralized Event-Triggered Online Learning for Safe Consensus of Multi-Agent Systems with Gaussian Process Regression](https://mlsanity.com/paper/2402.03174/) (2024)
- [Prompt2Auto: From Motion Prompt to Automated Control via Geometry-Invariant One-Shot Gaussian Process Learning](https://mlsanity.com/paper/2509.14040/) (2025)
- [Asynchronous Cooperative Online Learning for Multi-Robot Control under Computational Delays](https://mlsanity.com/paper/2608.29562/) (2026)
- [Event-triggered Control and Online Learning for Networked Systems under Computational Delays](https://mlsanity.com/paper/2608.29576/) (2026)

## Abstract (arXiv)

When the dynamics of systems are unknown, supervised machine learning techniques are commonly employed to infer models from data. Gaussian process (GP) regression is a particularly popular learning method for this purpose due to the existence of prediction error bounds. Moreover, GP models can be efficiently updated online, such that event-triggered online learning strategies can be pursued to ensure specified tracking accuracies. However, existing trigger conditions must be able to be evaluated at arbitrary times, which cannot be achieved in practice due to non-negligible computation times. Therefore, we first derive a delay-aware tracking error bound, which reveals an accuracy-delay trade-off. Based on this result, we propose a novel event trigger for GP-based online learning with computational delays, which we show to offer advantages over offline trained GP models for sufficiently small computation times. Finally, we demonstrate the effectiveness of the proposed event trigger for online learning in simulations.