The Impossibility of Parallelizing Boosting

Amin Karbasi, Kasper Green Larsen
1/23/2023
cs.LGcs.CCcs.DS

No confident code implementation found for this paper.

Abstract

The aim of boosting is to convert a sequence of weak learners into a strong learner. At their heart, these methods are fully sequential. In this paper, we investigate the possibility of parallelizing boosting. Our main contribution is a strong negative result, implying that significant parallelization of boosting requires an exponential blow-up in the total computing resources needed for training.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Optimal Parallelization of Boosting

89% match1 repo2024

BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models

78% match2025

Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey

76% match2024

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

76% match2023

Parallel Scaling Law for Language Models

75% match1 repo4802025

AdaBoost is not an Optimal Weak to Strong Learner

75% match2023

Cite this paper

@article{karbasi2023impossibility,
  title  = {The Impossibility of Parallelizing Boosting},
  author = {Amin Karbasi and Kasper Green Larsen},
  year   = {2023},
  eprint = {2301.09627},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2301.09627v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.09627.svg)](https://codeofpaper.com/paper/2301.09627)

Discussion