SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.02603 · 2019

Radial and Directional Posteriors for Bayesian Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ChangYong-Oh/RadiusDirectionPosteriors canonical 1 of 1
FunctionStatusWhere it lives
train Ran ChangYong-Oh/RadiusDirectionPosteriors/RadiusDirectionPosteriors/train_double_uci.py
pointer only (licence: NONE) · get_code("bdab7af08bcc2f37")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a new variational family for Bayesian neural networks. We decompose the variational posterior into two components, where the radial component captures the strength of each neuron in terms of its magnitude; while the directional component captures the statistical dependencies among the weight parameters. The dependencies learned via the directional density provide better modeling performance compared to the widely-used Gaussian mean-field-type variational family. In addition, the strength of input and output neurons learned via the radial density provides a structured way to compress neural networks. Indeed, experiments show that our variational family improves predictive performance and yields compressed networks simultaneously.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1902.02603")
get_code_for_paper("1902.02603")
have("1902.02603")

Connect an agent — have() is free.