Towards Efficient MCMC Sampling in Bayesian Neural Networks by
Exploiting Symmetry

Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry

6 April 2023

Theodore Papamarkou

Stephan Günnemann

Papers citing "Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry"

6 / 6 papers shown

Title
The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE Andrei Chernov Oleg Novitskij 73 0 0 24 Feb 2025
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models Yibin Wang Haizhou Shi Ligong Han Dimitris N. Metaxas Hao Wang BDL UQLM 118 8 0 28 Jan 2025
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 259 320 0 11 Sep 2022
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry Fabrizio Pittorino Antonio Ferraro Gabriele Perugini Christoph Feinauer Carlo Baldassi R. Zecchina 211 24 0 07 Feb 2022
Optimizing Mode Connectivity via Neuron Alignment N. Joseph Tatro Pin-Yu Chen Payel Das Igor Melnyk P. Sattigeri Rongjie Lai MoMe 240 80 0 05 Sep 2020
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 295 5,726 0 05 Dec 2016