Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis

Keyphrases

• Optimization Algorithm 100%
• Stationary Solution 100%
• Riemannian Manifold 100%
• Iteration Complexity Analysis 100%
• Primal-dual Optimization 100%
• Image Processing 50%
• Machine Learning 50%
• Sampling Methods 50%
• Optimization Problem 50%
• Statistical Learning 50%
• Nonsmooth 50%
• Stochastic Algorithm 50%
• Optimization Model 50%
• Numerical Results 50%
• Compressed Sensing 50%
• NP-hard 50%
• Line Search 50%
• Community Detection 50%
• Machine Learning Models 50%
• Euclidean Space 50%
• Linear Constraints 50%
• Optimality Conditions 50%
• Non-convexity 50%
• Tensor Robust Principal Component Analysis (TRPCA) 50%
• Embedded Structure 50%
• Primal-dual Algorithm 50%
• Iteration Complexity 50%
• Proximal Point Algorithm 50%
• Block Optimization 50%
• Sensing Image 50%
• Sparse Tensors 50%
• Tensor RPCA 50%
• Tensor Learning 50%
• Maximum Bisection 50%
• Bisection Problem 50%
• Riemannian Submanifold 50%
• Iteration Complexity Bound 50%
• Algorithm-based 50%

Mathematics

• Tensor 100%
• Riemannian Manifolds 100%
• Stationary Solution 66%
• Principal Component Analysis 66%
• Euclidean Space 33%
• Linear Constraint 33%
• Retraction 33%
• Riemannian Submanifold 33%
• Stochastics 33%
• Image Processing 33%
• Community Detection 33%
• Subproblem 33%
• Optimality Condition 33%