activity
20242026
collaborators

8 papers

cs.LG2026

A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics

Zheshun Wu, Renjie Zheng, Jinhang Zuo +2

This paper investigates a hybrid reinforcement learning setting in tabular Markov Decision Processes (MDPs), where an agent aims to learn an optimal policy by combining online inte…

cs.LG2026

CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon

Zheshun Wu, Ziyang Zhang, Changyao Lin +2

Recently, mobile edge computing (MEC)-enabled collaborative deep neural network (DNN) inference has emerged as a promising approach for delivering intelligent services to resource-…

cs.AI2025

Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization

Yi Zhang, Che Liu, Xiancong Ren +17

Developing a universal and versatile embodied intelligence system presents two primary challenges: the critical embodied data bottleneck, where real-world data is scarce and expens…

cs.LG2025

Understanding Generalization of Federated Learning: the Trade-off between Model Stability and Optimization

Dun Zeng, Zheshun Wu, Shiyu Liu +3

Federated Learning (FL) is a distributed learning approach that trains machine learning models across multiple devices while keeping their local data private. However, FL often fac…

cs.LG2025

IDInit: A Universal and Stable Initialization Method for Neural Network Training

Yu Pan, Chaozheng Wang, Zekai Wu +3

Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring st…

cs.LG2024

On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond

Dun Zeng, Zenglin Xu, Shiyu Liu +3

Federated averaging (FedAvg) is the most fundamental algorithm in Federated learning (FL). Previous theoretical results assert that FedAvg convergence and generalization degenerate…