# Event-triggered Learning

arXiv: https://arxiv.org/abs/1904.03042 · HTML: https://mlsanity.com/paper/1904.03042/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Event-Triggered Time-Varying Bayesian Optimization](https://mlsanity.com/paper/2208.10790/) (2022)
- [Distributed Event-Based Learning via ADMM](https://mlsanity.com/paper/2405.10618/) (2024)
- [Event-Triggered Reinforcement Learning Based Joint Resource Allocation for Ultra-Reliable Low-Latency V2X Communications](https://mlsanity.com/paper/2407.13947/) (2024)
- [Reactive Knowledge Representation and Asynchronous Reasoning](https://mlsanity.com/paper/2602.05625/) (2026)
- [Event-Based Communication in Distributed Q-Learning](https://mlsanity.com/paper/2109.01417/) (2021)
- [Robust Event-Driven Interactions in Cooperative Multi-Agent Learning](https://mlsanity.com/paper/2204.03361/) (2022)
- [Improving the Performance of Robust Control through Event-Triggered Learning](https://mlsanity.com/paper/2207.14252/) (2022)
- [A Systems-Theoretic View on the Convergence of Algorithms under Disturbances](https://mlsanity.com/paper/2512.17598/) (2025)
- [Event-triggered Control and Online Learning for Networked Systems under Computational Delays](https://mlsanity.com/paper/2608.29576/) (2026)

## Abstract (arXiv)

The efficient exchange of information is an essential aspect of intelligent collective behavior. Event-triggered control and estimation achieve some efficiency by replacing continuous data exchange between agents with intermittent, or event-triggered communication. Typically, model-based predictions are used at times of no data transmission, and updates are sent only when the prediction error grows too large. The effectiveness in reducing communication thus strongly depends on the quality of the prediction model. In this article, we propose event-triggered learning as a novel concept to reduce communication even further and to also adapt to changing dynamics. By monitoring the actual communication rate and comparing it to the one that is induced by the model, we detect a mismatch between model and reality and trigger model learning when needed. Specifically, for linear Gaussian dynamics, we derive different classes of learning triggers solely based on a statistical analysis of inter-communication times and formally prove their effectiveness with the aid of concentration inequalities.