# An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation

Source: [An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation](<https://www.sota2.com/research/paper/68fa66201e209131cea0e877>)

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

Data updated: 2025-10-25T21:43:30.383Z

Authors: Vincent Michalski, Vikram Voleti, Samira Ebrahimi Kahou, Anthony Ortiz, Pascal Vincent, Chris Pal, Doina Precup

Published: 2019-07-31T19:37:16.000Z

## Abstract

Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalization in certain tasks. Recently, alternative methods for normalizing feature activations in neural networks have been proposed. Among them, group normalization has been shown to yield similar, in some domains even superior performance to batch normalization. All these methods utilize a learned affine transformation after the normalization operation to increase representational power. Methods used in conditional computation define the parameters of these transformations as learnable functions of conditioning information. In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. We evaluate performances on the tasks of visual question answering, few-shot learning, and conditional image generation.

## 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/1908.00061>)

[PDF](<https://arxiv.org/pdf/1908.00061.pdf>)
