Research paper / RESOURCE PROFILE

1901-Accumulation bit-width Scaling

Publication: Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks. Published Jan 19, 2019.

arxiv.orgPublished Jan 19, 2019
Visit source website ↗
Screenshot unavailableResource information and source links remain available. 1901-Accumulation bit-width Scaling — reviewed source website screenshot
Reviewed source screenshot · recorded Oct 11, 2026 View source ↗

Overview

Publication: Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks. Published Jan 19, 2019.

Publication information

Publication title
Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks
Authors
Charbel Sakr, Naigang Wang, Chia-Yu Chen, Jungwook Choi, Ankur Agrawal, Naresh Shanbhag, Kailash Gopalakrishnan
Published
Jan 19, 2019
Last publication revision
Jan 19, 2019
Subject areas
cs.LG, stat.ML
Publication source
arxiv.org · abs/1901.06588v1 ↗

Source: arXiv API · observed Oct 11, 2026.

Source links & provenance

https://arxiv.org/abs/1901.06588 ↗

Discovery references

References explain how this resource entered the collection. They do not represent an endorsement.

Explore related resources

Screenshot unavailableResource information and source links remain available. DeepIntoStreams/TSFM_Finance — reviewed source website screenshot
RepositoryChecked capture

DeepIntoStreams/TSFM_Finance

github.com

the official implementation of the paper “Re(visiting) Time Series Foundation Models in Finance”.

GitHub stars
31
Language
Jupyter Notebook
Code license
Apache-2.0
foundation-modeltime-seriesresearch-lab
96 Authority 96 / 100 Cited by 2 resources in this directory 2 discovery sources Directory record updated: 2026-10-11 How scoring works →

Sign In

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.