DeepAI AI Chat
Log In Sign Up

Variance Networks: When Expectation Does Not Meet Your Expectations

by   Kirill Neklyudov, et al.

In this paper, we propose variance networks, a new model that stores the learned information in the variances of the network weights. Surprisingly, no information gets stored in the expectations of the weights, therefore if we replace these weights with their expectations, we would obtain a random guess quality prediction. We provide a numerical criterion that uses the loss curvature to determine which random variables can be replaced with their expected values, and find that only a small fraction of weights is needed for ensembling. Variance networks represent a diverse ensemble that is more robust to adversarial attacks than conventional low-variance ensembles. The success of this model raises several counter-intuitive implications for the training and application of Deep Learning models.


page 1

page 2

page 3

page 4


Learning Robust Kernel Ensembles with Kernel Average Pooling

Model ensembles have long been used in machine learning to reduce the va...

MUTEN: Boosting Gradient-Based Adversarial Attacks via Mutant-Based Ensembles

Deep Neural Networks (DNNs) are vulnerable to adversarial examples, whic...

Stratified Random Sampling for Dependent Inputs

A new approach of obtaining stratified random samples from statistically...

REDS: Random Ensemble Deep Spatial prediction

There has been a great deal of recent interest in the development of spa...

Sharp variance-entropy comparison for nonnegative gaussian quadratic forms

In this article we study quadratic forms in n independent standard norma...

ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables

To address the challenge of backpropagating the gradient through categor...

Introducing Graph Cumulants: What is the Variance of Your Social Network?

In an increasingly interconnected world, understanding and summarizing t...