Sparsified SGD with Memory

Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi

Feb-14-2026, 06:08:58 GMT–Neural Information Processing Systems

Several papers consider approaches that limit the number of bits to represent floating point numbers [13, 24, 31]. Recent work proposes adaptive tuning of the compression ratio [7].

artificial intelligence, conference, machine learning, (18 more...)

Neural Information Processing Systems

Feb-14-2026, 06:08:58 GMT

Conferences PDF

Add feedback

Country:
- Asia > Middle East
  - Jordan (0.04)
- Europe
  - France > Hauts-de-France
    - Nord > Lille (0.04)
  - Switzerland > Vaud
    - Lausanne (0.04)
- North America
  - Canada > Quebec
    - Montreal (0.04)
  - United States
    - Florida > Broward County
      - Fort Lauderdale (0.04)
    - Georgia > Fulton County
      - Atlanta (0.04)
    - Louisiana (0.04)
    - Massachusetts > Middlesex County
      - Cambridge (0.04)
    - New Jersey > Middlesex County
      - Piscataway (0.04)
- Oceania > Australia
  - New South Wales > Sydney (0.05)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.30)

Duplicate Docs Excel Report

Title
Sparsified SGD with Memory
Sparsified SGD with Memory

Similar Docs Excel Report more

Title	Similarity	Source
None found