The Fine-Grained Complexity of Gradient Computation for Training Large Language Models

Oct-10-2025, 05:45:47 GMT–Neural Information Processing Systems

To train an LLM, one needs to alternatingly run'forward' computations and'backward' computations.

arxiv preprint arxiv, large language model, machine learning, (16 more...)

Neural Information Processing Systems

Oct-10-2025, 05:45:47 GMT

Conferences PDF

Country:
- Asia > Afghanistan
  - Parwan Province > Charikar (0.04)
- North America > United States
  - California > Alameda County
    - Berkeley (0.04)
  - Virginia (0.04)
- South America > Brazil
  - Rio de Janeiro > Rio de Janeiro (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Neural Networks
    - Deep Learning (0.67)
  - Natural Language > Large Language Model (1.00)

Duplicate Docs Excel Report

Title
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models

Similar Docs Excel Report more

Title	Similarity	Source
None found