paper-with-me

Papers

Faster Boosting with Smaller Memory

2019-01-25 · NeurIPS 2019 12 · Julaiti Alafate, Yoav Freund

State-of-the-art implementations of boosting, such as XGBoost and LightGBM, can process large training sets extremely fast. However, this performance requires that the memory size is sufficient to hold a 2-3 multiple of the training set size. This paper presents an alternative approach to implementing the boosted trees, which achieves a significant speedup over XGBoost and LightGBM, especially when the memory size is small. This is achieved using a combination of three techniques: early stopping, effective sample size, and stratified sampling. Our experiments demonstrate a 10-100 speedup over XGBoost when the training data is too large to fit in memory.

📄 PDF Abstract BibTeX arXiv:1901.09047

Code (2)

arapat/sparrow 공식 구현
GUEEN/Sparrow

Similar Papers 제목 키워드 기반

Online Local Boosting: improving performance in online decision trees

2019-07-16 · Victor G. Turrisi da Costa, Saulo Martiello Mastelini, André C. Ponce de Leon Ferreira de Carvalho, Sylvio Barbon Jr

As more data are produced each day, and faster, data stream mining is growing in importance, making clear the need for algorithms able to fast process these data. Data stream mining algorithms are meant to be solutions t…

Out-of-Core GPU Gradient Boosting

2020-05-19 · Rong Ou

GPU-based algorithms have greatly accelerated many machine learning methods; however, GPU memory is typically smaller than main memory, limiting the size of training data. In this paper, we describe an out-of-core GPU gr…

BIG-bench Machine LearningGPU

TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting

2017-10-31 · Natalia Ponomareva, Soroush Radpour, Gilbert Hendry, Salem Haykal 외

TF Boosted Trees (TFBT) is a new open-sourced frame-work for the distributed training of gradient boosted trees. It is based on TensorFlow, and its distinguishing features include a novel architecture, automatic loss dif…

Accelerated Componentwise Gradient Boosting using Efficient Data Representation and Momentum-based Optimization

2021-10-07 · Daniel Schalk, Bernd Bischl, David Rügamer

Componentwise boosting (CWB), also known as model-based boosting, is a variant of gradient boosting that builds on additive models as base learners to ensure interpretability. CWB is thus often used in research areas whe…

Additive models

Compact Multi-Class Boosted Trees

2017-10-31 · Natalia Ponomareva, Thomas Colthurst, Gilbert Hendry, Salem Haykal 외

Gradient boosted decision trees are a popular machine learning technique, in part because of their ability to give good accuracy with small models. We describe two extensions to the standard tree boosting algorithm desig…