# Online Learning with Gated Linear Networks

arXiv: https://arxiv.org/abs/1712.01897 · HTML: https://mlsanity.com/paper/1712.01897/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2017.

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

- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Scaling Forward Gradient With Local Losses](https://mlsanity.com/paper/2210.03310/) (2022)
- [Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning](https://mlsanity.com/paper/2404.17617/) (2024)
- [Globally Gated Deep Linear Networks](https://mlsanity.com/paper/2210.17449/) (2022)
- [Levin Tree Search with Context Models](https://mlsanity.com/paper/2305.16945/) (2023)
- [The Implicit Bias of Gradient Descent on Generalized Gated Linear Networks](https://mlsanity.com/paper/2202.02649/) (2022)

## Abstract (arXiv)

This paper describes a family of probabilistic architectures designed for online learning under the logarithmic loss. Rather than relying on non-linear transfer functions, our method gains representational power by the use of data conditioning. We state under general conditions a learnable capacity theorem that shows this approach can in principle learn any bounded Borel-measurable function on a compact subset of euclidean space; the result is stronger than many universality results for connectionist architectures because we provide both the model and the learning procedure for which convergence is guaranteed.