# Fusing Multiple Algorithms for Heterogeneous Online Learning

arXiv: https://arxiv.org/abs/2312.05432 · HTML: https://mlsanity.com/paper/2312.05432/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 9 Dec 2023.

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

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Stochastic Gradient Descent as Approximate Bayesian Inference](https://mlsanity.com/paper/1704.04289/) (2017)
- [Three Factors Influencing Minima in SGD](https://mlsanity.com/paper/1711.04623/) (2017)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes](https://mlsanity.com/paper/1805.08114/) (2018)
- [Deep Model Fusion: A Survey](https://mlsanity.com/paper/2309.15698/) (2023)
- [Cross-Gradient Aggregation for Decentralized Learning from Non-IID data](https://mlsanity.com/paper/2103.02051/) (2021)
- [Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data](https://mlsanity.com/paper/2204.04452/) (2022)
- [Adaptive Online Learning](https://mlsanity.com/paper/1508.05170/) (2015)
- [Online Learning with Inexact Proximal Online Gradient Descent Algorithms](https://mlsanity.com/paper/1806.00202/) (2018)
- [Combining Online Learning Guarantees](https://mlsanity.com/paper/1902.09003/) (2019)
- [Remarks on input to state stability of perturbed gradient flows, motivated by model-free feedback control learning](https://mlsanity.com/paper/2108.02632/) (2021)
- [A continuous-time analysis of distributed stochastic gradient](https://mlsanity.com/paper/1812.10995/) (2018)
- [Multi-Agent Distributed Reinforcement Learning for Making Decentralized Offloading Decisions](https://mlsanity.com/paper/2204.02267/) (2022)
- [A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows](https://mlsanity.com/paper/2105.08832/) (2021)

## Built on by (most cited first, 1 of 1)

- [Online Residual Learning from Offline Experts for Pedestrian Tracking](https://mlsanity.com/paper/2409.04069/) (2024)

## Abstract (arXiv)

This study addresses the challenge of online learning in contexts where agents accumulate disparate data, face resource constraints, and use different local algorithms. This paper introduces the Switched Online Learning Algorithm (SOLA), designed to solve the heterogeneous online learning problem by amalgamating updates from diverse agents through a dynamic switching mechanism contingent upon their respective performance and available resources. We theoretically analyze the design of the selecting mechanism to ensure that the regret of SOLA is bounded. Our findings show that the number of changes in selection needs to be bounded by a parameter dependent on the performance of the different local algorithms. Additionally, two test cases are presented to emphasize the effectiveness of SOLA, first on an online linear regression problem and then on an online classification problem with the MNIST dataset.