No article text was recorded for this version.
post-averaging normalization update
Version 1 of 110 papers16 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits
- Blog: Averaging Weights Leads to Wider Optima and Better Generalization
- Blog: Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging
- Blog: Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift
- Blog: REPAIR: REnormalizing Permuted Activations for Interpolation Repair
- Blog: Toward Data Efficient Model Merging between Different Datasets without Performance Degradation
- Blog: WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
- Blog: Continual Learning with Weight Interpolation
- Blog: Adversarial Training with Stochastic Weight Average
- Blog: Stochastic Weight Averaging in Parallel: Large-Batch Training That Generalizes Well
History & citation
Current · Permanent link
- This direction split from Recalibrating Batch Normalization Statistics (80% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_post_averaging_normalization_update_ac2e03e4,
title = {post-averaging normalization update},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/post-averaging-normalization-update/rdr_ac2e03e463324a65ba9511020f0b1a68},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_post_averaging_normalization_update_ac2e03e4_v1,
title = {post-averaging normalization update},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/post-averaging-normalization-update/rdr_ac2e03e463324a65ba9511020f0b1a68/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}