Timezone: »
Diversity is All You Need to Improve Bayesian Model Averaging
Yashvir Singh Grewal · Thang Bui
Event URL: https://openreview.net/forum?id=agwGfBQmFuG »
Existing approximate inference techniques produce predictive distributions that are quite distinct from the predictive distribution of the gold-standard Hamiltonian Monte Carlo. In this work, we bring the predictive distribution produced by deep ensembles more closer to the Hamiltonian Monte Carlo predictive distribution by increasing the diversity within the ensembles. The proposed approach outperforms the existing approximate inference methods and is also currently ranked the highest in the Approximate Inference competition at NeurIPS 2021.
Author Information
Yashvir Singh Grewal (Monash University)
Thang Bui (University of Sydney)
More from the Same Authors
-
2021 : Variance-Seeking Meta-Exploration to Handle Out-of-Distribution Tasks »
Yashvir Singh Grewal · Sarah Goodwin -
2021 : Biases in variational Bayesian neural networks »
Thang Bui -
2015 Poster: Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels »
Felipe Tobar · Thang Bui · Richard Turner -
2015 Spotlight: Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels »
Felipe Tobar · Thang Bui · Richard Turner -
2014 Poster: Tree-structured Gaussian Process Approximations »
Thang Bui · Richard Turner -
2014 Spotlight: Tree-structured Gaussian Process Approximations »
Thang Bui · Richard Turner