Latent Projection BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

11/16/2018
by   Melanie F. Pradier, et al.
0

While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing uncertainty over the parameters of these models (in a Bayesian setting) is challenging because of the high-dimensionality of the network parameter space and the correlations between these parameters. In this paper, we introduce a novel framework for variational inference for Bayesian neural networks that (1) encodes complex distributions in high-dimensional parameter space with representations in a low-dimensional latent space and (2) performs inference efficiently on the low-dimensional representations. Across a large array of synthetic and real-world datasets, we show that our method improves uncertainty characterization and model generalization when compared with methods that work directly in the parameter space.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/17/2019

Subspace Inference for Bayesian Deep Learning

Bayesian inference was once a gold standard for learning with neural net...
research
01/25/2023

Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems

We present a data-driven, space-time continuous framework to learn surro...
research
02/01/2016

Fast inference of ill-posed problems within a convex space

In multiple scientific and technological applications we face the proble...
research
02/19/2020

A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs

Creating a database of 21cm brightness temperature signals from the Epoc...
research
03/01/2023

Multi-task neural networks by learned contextual inputs

This paper explores learned-context neural networks. It is a multi-task ...
research
05/13/2023

Grasping Extreme Aerodynamics on a Low-Dimensional Manifold

Modern air vehicles perform a wide range of operations, including transp...

Please sign up or login with your details

Forgot password? Click here to reset