paper-with-me

Papers

Neural Bootstrapper

2020-10-02 · NeurIPS 2021 12 · Minsuk Shin, Hyungjoo Cho, Hyun-seok Min, Sungbin Lim

Bootstrapping has been a primary tool for ensemble and uncertainty quantification in machine learning and statistics. However, due to its nature of multiple training and resampling, bootstrapping deep neural networks is computationally burdensome; hence it has difficulties in practical application to the uncertainty estimation and related tasks. To overcome this computational bottleneck, we propose a novel approach called \emph{Neural Bootstrapper} (NeuBoots), which learns to generate bootstrapped neural networks through single model training. NeuBoots injects the bootstrap weights into the high-level feature layers of the backbone network and outputs the bootstrapped predictions of the target, without additional parameters and the repetitive computations from scratch. We apply NeuBoots to various machine learning tasks related to uncertainty quantification, including prediction calibrations in image classification and semantic segmentation, active learning, and detection of out-of-distribution samples. Our empirical results show that NeuBoots outperforms other bagging based methods under a much lower computational cost without losing the validity of bootstrapping.

📄 PDF Abstract BibTeX arXiv:2010.01051

Code (2)

sungbinlim/GBS 공식 구현 pytorch
sungbinlim/neuboots 공식 구현 pytorch

Tasks

Active LearningBIG-bench Machine Learningimage-classificationImage ClassificationSemantic SegmentationUncertainty Quantification

Similar Papers 제목 키워드 기반

Are Long-LLMs A Necessity For Long-Context Tasks?

2024-05-24 · Hongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao 외

The learning and deployment of long-LLMs remains a challenging problem despite recent progresses. In this work, we argue that the long-LLMs are not a necessity to solve long-context tasks, as common long-context tasks ar…