# Controlling Covariate Shift using Balanced Normalization of Weights

Source: [Controlling Covariate Shift using Balanced Normalization of Weights](<https://www.sota2.com/research/paper/68fa65ba1e209131cea0be39>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:33:37.375Z

Authors: Aaron Defazio, L\\'eon Bottou

Published: 2018-12-11T17:12:50.000Z

## Abstract

We introduce a new normalization technique that exhibits the fast convergence properties of batch normalization using a transformation of layer weights instead of layer outputs. The proposed technique keeps the contribution of positive and negative weights to the layer output balanced. We validate our method on a set of standard benchmarks including CIFAR-10/100, SVHN and ILSVRC 2012 ImageNet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1812.04549>)

[PDF](<https://arxiv.org/pdf/1812.04549.pdf>)