# Universal Codes from Switching Strategies

arXiv: https://arxiv.org/abs/1311.6536 · HTML: https://mlsanity.com/paper/1311.6536/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2013.

## Built on by (most cited first, 3 of 3)

- [Improved Regret Bounds for Tracking Experts with Memory](https://mlsanity.com/paper/2106.13021/) (2021)
- [Evaluating Representations with Readout Model Switching](https://mlsanity.com/paper/2302.09579/) (2023)
- [Change-point Detection and Segmentation of Discrete Data using Bayesian Context Trees](https://mlsanity.com/paper/2203.04341/) (2022)

## Abstract (arXiv)

We discuss algorithms for combining sequential prediction strategies, a task which can be viewed as a natural generalisation of the concept of universal coding. We describe a graphical language based on Hidden Markov Models for defining prediction strategies, and we provide both existing and new models as examples. The models include efficient, parameterless models for switching between the input strategies over time, including a model for the case where switches tend to occur in clusters, and finally a new model for the scenario where the prediction strategies have a known relationship, and where jumps are typically between strongly related ones. This last model is relevant for coding time series data where parameter drift is expected. As theoretical ontributions we introduce an interpolation construction that is useful in the development and analysis of new algorithms, and we establish a new sophisticated lemma for analysing the individual sequence regret of parameterised models.