paper-with-me

Papers

Tricks and Plug-ins for Gradient Boosting with Transformers

2025-08-04 · Biyi Fang, Truong Vo, Jean Utke, Diego Klabjan arxiv

Transformer architectures dominate modern NLP but often demand heavy computational resources and intricate hyperparameter tuning. To mitigate these challenges, we propose a novel framework, BoostTransformer, that augments transformers with boosting principles through subgrid token selection and importance-weighted sampling. Our method incorporates a least square boosting objective directly into the transformer pipeline, enabling more efficient training and improved performance. Across multiple fine-grained text classification benchmarks, BoostTransformer demonstrates both faster convergence and higher accuracy, surpassing standard transformers while minimizing architectural search overhead.

📄 PDF Abstract BibTeX arXiv:2508.02924

Code (0)

등록된 구현이 없습니다.

Tasks

Text Classification

Similar Papers 제목 키워드 기반

Tricks and Plugins to GBM on Images and Sequences

2022-03-01 · Biyi Fang, Jean Utke, Diego Klabjan

Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learn…

feature selection

Tricks and Plug-ins for Gradient Boosting in Image Classification

2025-07-30 · Biyi Fang, Truong Vo, Jean Utke, Diego Klabjan arxiv

Convolutional Neural Networks (CNNs) have achieved remarkable success across a wide range of machine learning tasks by leveraging hierarchical feature learning through deep architectures. However, the large number of lay…

Image Classification

Gradient Boosting With Piece-Wise Linear Regression Trees

2018-02-15 · Yu Shi, Jian Li, Zhize Li

Gradient Boosted Decision Trees (GBDT) is a very successful ensemble learning algorithm widely used across a variety of applications. Recently, several variants of GBDT training algorithms and implementations have been d…

Ensemble Learningregression

Transformer tricks: Precomputing the first layer

2024-02-20 · Nils Graef

This micro-paper describes a trick to speed up inference of transformers with RoPE (such as LLaMA, Mistral, PaLM, and Gemma). For these models, a large portion of the first transformer layer can be precomputed, which res…

Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting

2026-03-08 · Yael S. Elmatad arxiv

Gradient boosting still dominates Transformers on tabular benchmarks. Our tokenizer uses a deliberately simplistic discretized vocabulary so we can highlight how even basic tokenization unlocks the power of attention on …