DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

Oct-8-2025, 04:24:11 GMT–Neural Information Processing Systems

This paper proposes a new easy-to-implement parameter-free gradient-based optimizer: DoWG (Distance over Weighted Gradients).

artificial intelligence, gradient descent, machine learning, (14 more...)

Neural Information Processing Systems

Oct-8-2025, 04:24:11 GMT

Conferences PDF

Country:
- Africa > Ethiopia
  - Addis Ababa > Addis Ababa (0.04)
- Asia
  - Japan > Kyūshū & Okinawa
    - Okinawa (0.04)
  - Middle East > Israel
    - Haifa District > Haifa (0.04)
  - Russia (0.04)
- Europe
  - Russia (0.04)
  - Spain > Catalonia
    - Barcelona Province > Barcelona (0.04)
  - United Kingdom > England
    - Cambridgeshire > Cambridge (0.04)
    - Greater London > London (0.04)
- North America
  - Canada
    - British Columbia > Vancouver (0.04)
    - Ontario > Toronto (0.04)
    - Quebec > Montreal (0.04)
  - United States > California
    - Los Angeles County > Long Beach (0.14)
    - San Diego County > San Diego (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Statistical Learning
    - Gradient Descent (0.68)
  - Representation & Reasoning > Optimization (1.00)