Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Oct-8-2025, 16:47:08 GMT–Neural Information Processing Systems

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training.

eigenvalue, machine learning, natural language, (19 more...)

Neural Information Processing Systems

Oct-8-2025, 16:47:08 GMT

Conferences PDF

Country:
- Asia
  - China > Shanghai
    - Shanghai (0.04)
  - Myanmar > Tanintharyi Region
    - Dawei (0.04)
- Europe > United Kingdom
  - England > Oxfordshire > Oxford (0.04)
- North America > United States
  - Colorado > Boulder County
    - Boulder (0.04)
  - Michigan (0.04)
- South America > Chile
  - Santiago Metropolitan Region > Santiago Province > Santiago (0.04)

Genre:
- Research Report > New Finding (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Neural Networks
    - Deep Learning (1.00)
  - Natural Language (1.00)