Efficient Decentralized Stochastic Gradient Descent Method for Nonconvex Finite-Sum Optimization Problems
Keywords:Machine Learning (ML)
AbstractDecentralized stochastic gradient descent methods have attracted increasing interest in recent years. Numerous methods have been proposed for the nonconvex finite-sum optimization problem. However, existing methods have a large sample complexity, slowing down the empirical convergence speed. To address this issue, in this paper, we proposed a novel decentralized stochastic gradient descent method for the nonconvex finite-sum optimization problem, which enjoys a better sample and communication complexity than existing methods. To the best of our knowledge, our work is the first one achieving such favorable sample and communication complexities. Finally, we have conducted extensive experiments and the experimental results have confirmed the superior performance of our proposed method.
How to Cite
Zhan, W., Wu, G., & Gao, H. (2022). Efficient Decentralized Stochastic Gradient Descent Method for Nonconvex Finite-Sum Optimization Problems. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 9006-9013. https://doi.org/10.1609/aaai.v36i8.20884
AAAI Technical Track on Machine Learning III