paper-with-me

Papers

Model Selection in Bayesian Neural Networks via Horseshoe Priors

2017-05-29 · Soumya Ghosh, Finale Doshi-Velez

Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even choosing the number of nodes---remains an open question. In this work, we apply a horseshoe prior over node pre-activations of a Bayesian neural network, which effectively turns off nodes that do not help explain the data. We demonstrate that our prior prevents the BNN from under-fitting even when the number of nodes required is grossly over-estimated. Moreover, this model selection over the number of nodes doesn't come at the expense of predictive or computational performance; in fact, we learn smaller networks with comparable predictive performance to current approaches.

📄 PDF Abstract BibTeX arXiv:1705.10388

Code (1)

SoumyaTGhosh/hs-bnn-public 공식 구현

Tasks

Model SelectionOpen-Ended Question Answering

Similar Papers 제목 키워드 기반

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors

2018-06-13 · ICML 2018 7 · Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez

Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even choosing the number of nodes---remains an …

Model SelectionOpen-Ended Question Answeringreinforcement-learningReinforcement Learning+1

Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods

2026-04-04 · Hao Xiao arxiv

Choosing between classical and Bayesian sparse regression methods involves a real trade-off: penalized estimators like Lasso run in milliseconds but give no uncertainty estimates,while Horseshoe and Spike-and-Slab priors…

Semi-parametric Expert Bayesian Network Learning with Gaussian Processes and Horseshoe Priors

2024-01-29 · Yidou Weng, Finale Doshi-Velez

This paper proposes a model learning Semi-parametric rela- tionships in an Expert Bayesian Network (SEBN) with linear parameter and structure constraints. We use Gaussian Pro- cesses and a Horseshoe prior to introduce mi…

Gaussian Processes

False Discovery Rate Control via Frequentist-assisted Horseshoe

2025-02-08 · Qiaoyu Liang, Zihan Zhu, Ziang Fu, Michael Evans

The horseshoe prior, a widely used handy alternative to the spike-and-slab prior, has proven to be an exceptional default global-local shrinkage prior in Bayesian inference and machine learning. However, designing tests …

Bayesian Inference

Horseshoe Regularization for Machine Learning in Complex and Deep Models

2019-04-24 · Anindya Bhadra, Jyotishka Datta, Yunfan Li, Nicholas G. Polson

Since the advent of the horseshoe priors for regularization, global-local shrinkage methods have proved to be a fertile ground for the development of Bayesian methodology in machine learning, specifically for high-dimens…

BIG-bench Machine Learningregression