Ke Wei
8 papers · 2019–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (21) π₯ Unstoppable Β· Bronze
β
The Questioner
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory
(5)
Reinforcement Learning
(3)
Methods
(3)
Artificial Intelligence
(2)
Deep Learning
(2)
Mathematics & Optimization
(2)
Architectures
(2)
Core Methods
(2)
Optimization
(2)
Computer Vision
(1)
Bayesian & Probabilistic
(1)
Core AI
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
variance reduction
(2)
decentralized optimization
(2)
natural policy gradient
(2)
matrix decomposition
(1)
reinforcement learning
(1)
semantic segmentation
(1)
multi-agent reinforcement learning
(1)
policy optimization
(1)
bayesian inference
(1)
deep learning
(1)
kl divergence
(1)
convergence analysis
(1)
sample complexity
(1)
image generation
(1)
stochastic gradient
(1)
model fusion
(1)
kullback-leibler divergence
(1)
policy iteration
(1)
federated learning
(1)
riemannian optimization
(1)
Papers
Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance
AAAI 2026
Ο-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
ICLR 2025
On the Convergence of Projected Policy Gradient for Any Constant Step Sizes
JMLR 2025
Decentralized Natural Policy Gradient with Variance Reduction for Collaborative Multi-Agent Reinforcement Learning
JMLR 2024
Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion
JMLR 2023
Probabilistic Fusion of Neural Networks that
Incorporates Global Information
ACML 2022
Is Attention Better Than Matrix Decomposition?
ICLR 2021
Accelerated Alternating Projections for Robust Principal Component Analysis
JMLR 2019