Efficient Tuning and Inference for Large Language Models on Textual Graphs
Abstract
The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process. The proposed approach is based on distributed optimization algorithms, which can be interpreted as primal-dual ordinary differential equation (ODE) dynamics subject to null-space constraints. Based on the exponential convergence behavior of the primal-dual ODE dynamics subject to null-space constraints, we examine the behavior of the final iterate in various distributed TD-learning scenarios, considering both constant and diminishing step-sizes and incorporating both i.i.d. and Markovian observation models. Unlike existing methods, the proposed algorithm does not require the assumption that the underlying communication network structure is characterized by a doubly stochastic matrix.
Cite
Text
Zhu et al. "Efficient Tuning and Inference for Large Language Models on Textual Graphs." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/634Markdown
[Zhu et al. "Efficient Tuning and Inference for Large Language Models on Textual Graphs." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/zhu2024ijcai-efficient/) doi:10.24963/ijcai.2024/634BibTeX
@inproceedings{zhu2024ijcai-efficient,
title = {{Efficient Tuning and Inference for Large Language Models on Textual Graphs}},
author = {Zhu, Yun and Wang, Yaoke and Shi, Haizhou and Tang, Siliang},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {5734-5742},
doi = {10.24963/ijcai.2024/634},
url = {https://mlanthology.org/ijcai/2024/zhu2024ijcai-efficient/}
}