Stochastic Optimization

PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities

Recently, min-max optimization problems have received increasing attention due to their wide range of applications in machine learning …

Zhuqing Liu, Xin Zhang, Songtao Lu, Jia Liu

Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning

In recent years, decentralized bilevel optimization has gained significant attention thanks to its versatility in modeling a wide range …

Zhuqing Liu, Xin Zhang, Prashant Khanduri, Songtao Lu, Jia Liu

INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks

In recent years, decentralized bilevel optimization problems have received increasing attention in the networking and machine learning …

Zhuqing Liu, Xin Zhang, Prashant Khanduri, Songtao Lu, Jia Liu

NET-FLEET: Achieving linear convergence speedup for fully decentralized federated learning with heterogeneous data

Federated learning (FL) has received a surge of interest in recent years thanks to its benefits in data privacy protection, efficient …

Xin Zhang, Minghong Fang, Zhuqing Liu, Haibo Yang, Jia Liu, Zhengyuan Zhu

SYNTHESIS: A semi-asynchronous path-integrated stochastic gradient method for distributed learning in computing clusters

To increase the training speed of distributed learning, recent years have witnessed a significant amount of interest in developing both …

Zhuqing Liu, Xin Zhang, Jia Liu

SAGDA: Achieving O(ε−2) Communication Complexity in Federated Min-Max Learning

Federated min-max learning has received increasing attention in recent years thanks to its wide range of applications in various learning paradigms. In this paper, we propose a new algorithmic framework called stochastic sampling averaging gradient descent ascent (SAGDA), which yields an O(ε−2) communication complexity that is orders of magnitude lower than the state of the art.

Haibo Yang, Zhuqing Liu, Xin Zhang, Jia Liu

Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (MARL) has found many scientific and engineering applications. In this paper, we focus on decentralized MARL policy evaluation with nonlinear function approximation and propose efficient optimization algorithms.

Xin Zhang, Zhuqing Liu, Jia Liu, Zhengyuan Zhu, Songtao Lu

Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning

GT-STORM: Taming sample, communication, and memory complexities in decentralized non-convex learning

Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in …

Xin Zhang, Jia Liu, Zhengyuan Zhu, Elizabeth Serena Bentley

Low Sample and Communication Complexities in Decentralized Learning: A Triple Hybrid Approach

Decentralized optimization has received increasing attention in recent years, due to its advantages in system robustness, data privacy …

Xin Zhang, Jia Liu, Zhengyuan Zhu, Elizabeth Serena Bentley

Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning

Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing …

Xin Zhang, Jia Liu, Zhengyuan Zhu