11 papers
Decentralized Pose Graph Riemannian Optimization for Object-based Multi-Robot SLAM
Yixian Zhao, Yan Huang, Yang Xu +2
Pose graph optimization (PGO) is a key back-end component for state estimation in networked multi-robot simultaneous localization and mapping (SLAM). In object-based multi-robot SL…
DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication
Zehan Zhu, Heng Zhao, Yan Huang +3
In this paper, we propose a Differentially Private Stochastic Gradient Push with Compressed communication (termed DP-CSGP) for decentralized learning over directed graphs. Differen…
Bandwidth-Aware Network Topology Optimization for Decentralized Learning
Yipeng Shen, Zehan Zhu, Yan Huang +3
Network topology is critical for efficient parameter synchronization in distributed learning over networks. However, most existing studies do not account for bandwidth limitations…
Beyond Scaffold: A Unified Spatio-Temporal Gradient Tracking Method
Yan Huang, Jinming Xu, Jiming Chen +1
In distributed and federated learning algorithms, communication overhead is often reduced by performing multiple local updates between communication rounds. However, due to data he…
Pareto-optimal Trade-offs Between Communication and Computation with Flexible Gradient Tracking
Yan Huang, Jinming Xu, Li Chai +2
This paper addresses distributed stochastic optimization problems under non-i.i.d. data, focusing on the inherent trade-offs between communication and computational efficiency. To…
An Optimistic Gradient Tracking Method for Distributed Minimax Optimization
Yan Huang, Jinming Xu, Jiming Chen +1
This paper studies the distributed minimax optimization problem over networks. To enhance convergence performance, we propose a distributed optimistic gradient tracking method, ter…
CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems
Jiaxi Huang, Yan Huang, Yixian Zhao +2
Collaborative learning enhances the performance and adaptability of multi-robot systems in complex tasks but faces significant challenges due to high communication overhead and dat…
Dyn-DP: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee
Zehan Zhu, Yan Huang, Xin Wang +2
Most existing decentralized learning methods with differential privacy (DP) guarantee rely on constant gradient clipping bounds and fixed-level DP Gaussian noises for each node thr…
Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
Yan Huang, Xiang Li, Yipeng Shen +2
In this paper, we show that applying adaptive methods directly to distributed minimax problems can result in non-convergence due to inconsistency in locally computed adaptive steps…
PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds
Zehan Zhu, Yan Huang, Xin Wang +1
In this paper, we propose a differentially private decentralized learning method (termed PrivSGP-VR) which employs stochastic gradient push with variance reduction and guarantees $…
Distributed Stochastic Bilevel Optimization: Improved Complexity and Heterogeneity Analysis
Youcheng Niu, Jinming Xu, Ying Sun +2
This paper consider solving a class of nonconvex-strongly-convex distributed stochastic bilevel optimization (DSBO) problems with personalized inner-level objectives. Most existing…