成果/Result
- Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion被引量：2收藏
- 作者：Wang, Haifeng Chen, Jinchi Wei, Ke
- 机构：Fudan Univ;China Mobile Zhejiang Res & Innovat Inst;East China Univ Sci & Technol
- 来源：JOURNAL OF MACHINE LEARNING RESEARCH 2023
- 关键词：low rank tensor completion Tucker decomposition Riemannian gradient entrywise convergence implicit regularization leave-one-out
- Global Convergence of Natural Policy Gradient with Hessian-Aided Momentum Variance Reduction被引量：1收藏
- 作者：Feng, Jie Wei, Ke Chen, Jinchi
- 机构：Fudan Univ;East China Univ Sci & Technol
- 来源：JOURNAL OF SCIENTIFIC COMPUTING 2024
- 关键词：Natural policy gradient Reinforcement learning Sample complexity Variance reduction
- A zeroth-order variance-reduced method for decentralized stochastic non-convex optimization被引量：0收藏
- 作者：Chen, Hongxu Chen, Jinchi Wei, Ke
- 机构：Fudan Univ;East China Univ Sci & Technol
- 来源：OPTIMIZATION 2025
- 关键词：Decentralized non-convex optimization zeroth-order method variance reduction stochastic optimization linear speedup
- On the linear convergence of policy gradient under Hadamard parameterization被引量：0收藏
- 作者：Liu, Jiacai Chen, Jinchi Wei, Ke
- 机构：Fudan Univ;East China Univ Sci & Technol
- 来源：INFORMATION AND INFERENCE-A JOURNAL OF THE IMA 2025
- 关键词：policy gradient Hadamard parameterization linear convergence sub-optimal probability
- Fast and provable simultaneous blind super-Resolution and demixing for point source signals via scaled gradient descent被引量：0收藏
- 作者：Chen, Jinchi Xiang, Zeyu
- 机构：East China Univ Sci & Technol
- 来源：DIGITAL SIGNAL PROCESSING 2026
- 关键词：low rank matrix recovery scaled gradient descent Simultaneous blind super-resolution and demixing
- Decentralized Natural Policy Gradient with Variance Reduction for Collaborative Multi-Agent Reinforcement Learning被引量：0收藏
- 作者：Chen, Jinchi Feng, Jie Gao, Weiguo Wei, Ke
- 机构：Fudan Univ;East China Univ Sci & Technol;Fudan Univ
- 来源：JOURNAL OF MACHINE LEARNING RESEARCH 2024
- 关键词：multi-agent reinforcement learning natural policy gradient decentralized optimization variance reduction
