# Batch Universal Prediction

arXiv: https://arxiv.org/abs/2402.03901 · HTML: https://mlsanity.com/paper/2402.03901/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Builds on (most cited first, 2 of 2)

- [On Learning Markov Chains](https://mlsanity.com/paper/1810.11754/) (2018)
- [Learning, compression, and leakage: Minimising classification error via meta-universal compression principles](https://mlsanity.com/paper/2010.07382/) (2020)

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

- [From Markov to Laplace: How Mamba In-Context Learns Markov Chains](https://mlsanity.com/paper/2502.10178/) (2025)
- [Information-Theoretic Framework for Understanding Modern Machine-Learning](https://mlsanity.com/paper/2506.07661/) (2025)
- [The Conditional Regret-Capacity Theorem for Batch Universal Prediction](https://mlsanity.com/paper/2508.10282/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have recently gained much popularity due to their surprising ability at generating human-like English sentences. LLMs are essentially predictors, estimating the probability of a sequence of words given the past. Therefore, it is natural to evaluate their performance from a universal prediction perspective. In order to do that fairly, we introduce the notion of batch regret as a modification of the classical average regret, and we study its asymptotical value for add-constant predictors, in the case of memoryless sources and first-order Markov sources.