# Optimal Parallelization of Boosting

arXiv: https://arxiv.org/abs/2408.16653 · HTML: https://mlsanity.com/paper/2408.16653/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 29 Aug 2024.

## Builds on (most cited first, 4 of 4)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Optimal Weak to Strong Learning](https://mlsanity.com/paper/2206.01563/) (2022)
- [The Impossibility of Parallelizing Boosting](https://mlsanity.com/paper/2301.09627/) (2023)
- [The Cost of Parallelizing Boosting](https://mlsanity.com/paper/2402.15145/) (2024)

## Built on by (most cited first, 2 of 2)

- [Statistical Inference for Gradient Boosting Regression](https://mlsanity.com/paper/2509.23127/) (2025)
- [Tight Generalization Bound for AdaBoost](https://mlsanity.com/paper/2607.26838/) (2026)

## Abstract (arXiv)

Recent works on the parallel complexity of Boosting have established strong lower bounds on the tradeoff between the number of training rounds p and the total parallel work per round t. These works have also presented highly non-trivial parallel algorithms that shed light on different regions of this tradeoff. Despite these advancements, a significant gap persists between the theoretical lower bounds and the performance of these algorithms across much of the tradeoff space. In this work, we essentially close this gap by providing both improved lower bounds on the parallel complexity of weak-to-strong learners, and a parallel Boosting algorithm whose performance matches these bounds across the entire p vs.~t compromise spectrum, up to logarithmic factors. Ultimately, this work settles the true parallel complexity of Boosting algorithms that are nearly sample-optimal.