A gossip algorithm for convex consensus optimization over networks

By Jie Lu, Choon Yik Tang, Paul R. Regier, Travis D. Bow. 2010

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiangru Lian
2. Ce Zhang
3. Huan Zhang
4. Ji Liu
5. Cho-Jui Hsieh
6. Hanlin Tang
7. Jianyu Wang
8. Hao Yu

Citations in the corpus

• Asynchronous Decentralized Parallel Stochastic Gradient Descent (2017, methodology): “For decentralized algorithms used for optimization problems, Lu et al. [2010] proposed two non-gradient-based algorithms for solving one-dimensional unconstrained convex optimization problems where the objective on each node is strictly convex, by calculating the inverse function of the derivative…”
• Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent (2017, methodology): “Mokhtari and Ribeiro [2016] analyzed decentralized SAG and SAGA algorithms. They are not shown to have speedup, and a table of all stochastic gradients need to be saved in the storage or memory. Decentralized gradient descent on convex and strongly convex problems was analyzed in Yuan et al. [2016].”