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

Authors: Josh Alman, Zhao Song

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper is a purely theoretical paper, and it doesn t include any experiments.
Researcher Affiliation Academia Josh Alman Department of Computer Science Columbia University josh@cs.columbia.edu Zhao Song Simons Institute for the Theory of Computing University of California, Berkeley magic.linuxkde@gmail.com
Pseudocode No The paper describes algorithmic ideas and steps but does not include any explicit pseudocode blocks or algorithms labeled as such.
Open Source Code No This paper is a purely theoretical paper, and it doesn t include any experiments.
Open Datasets No This paper is a purely theoretical paper, and it doesn t include any experiments.
Dataset Splits No This paper is a purely theoretical paper, and it doesn t include any experiments.
Hardware Specification No This paper is a purely theoretical paper, and it doesn t include any experiments.
Software Dependencies No This paper is a purely theoretical paper, and it doesn t include any experiments.
Experiment Setup No This paper is a purely theoretical paper, and it doesn t include any experiments.