Rethinking gradient sparsification as total error minimization

Feb-8-2026, 10:07:40 GMT–Neural Information Processing Systems

We identify that the total error -- the sum of the compression errors for all iterations -- encapsulates sparsification throughout training.

artificial intelligence, compressor, machine learning, (16 more...)

Neural Information Processing Systems

Feb-8-2026, 10:07:40 GMT

Conferences PDF

Country:
- Europe > Italy
  - Calabria > Catanzaro Province > Catanzaro (0.04)
- North America
  - Canada > Ontario
    - Toronto (0.14)
  - United States > Kansas (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks > Deep Learning (0.69)
    - Statistical Learning (0.95)
  - Representation & Reasoning (0.94)

Duplicate Docs Excel Report

Title
447b0408b80078338810051bb38b177f-Paper.pdf

Similar Docs Excel Report more

Title	Similarity	Source
None found