# Gossiped and Quantized Online Multi-Kernel Learning

arXiv: https://arxiv.org/abs/2301.09848 · HTML: https://mlsanity.com/paper/2301.09848/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 24 Jan 2023.

## Builds on (most cited first, 7 of 7)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication](https://mlsanity.com/paper/1902.00340/) (2019)
- [QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding](https://mlsanity.com/paper/1610.02132/) (2016)
- [Decentralized Deep Learning with Arbitrary Communication Compression](https://mlsanity.com/paper/1907.09356/) (2019)
- [Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems](https://mlsanity.com/paper/2101.03367/) (2021)
- [Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamics](https://mlsanity.com/paper/1712.09983/) (2017)
- [Distributed Online Learning with Multiple Kernels](https://mlsanity.com/paper/2102.12733/) (2021)

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

- [Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation](https://mlsanity.com/paper/2308.00263/) (2023)
- [Quantized and Asynchronous Federated Learning](https://mlsanity.com/paper/2410.00242/) (2024)
- [Communication Compression for Distributed Learning without Control Variates](https://mlsanity.com/paper/2412.04538/) (2024)
- [Decentralized Optimization in Time-Varying Networks with Arbitrary Delays](https://mlsanity.com/paper/2405.19513/) (2024)
- [Communication Compression for Distributed Learning with Aggregate and Server-Guided Feedback](https://mlsanity.com/paper/2512.22623/) (2025)
- [Decentralized Parameter-Free Online Learning with Compressed Gossip](https://mlsanity.com/paper/2605.27831/) (2026)

## Abstract (arXiv)

In instances of online kernel learning where little prior information is available and centralized learning is unfeasible, past research has shown that distributed and online multi-kernel learning provides sub-linear regret as long as every pair of nodes in the network can communicate (i.e., the communications network is a complete graph). In addition, to manage the communication load, which is often a performance bottleneck, communications between nodes can be quantized. This letter expands on these results to non-fully connected graphs, which is often the case in wireless sensor networks. To address this challenge, we propose a gossip algorithm and provide a proof that it achieves sub-linear regret. Experiments with real datasets confirm our findings.