Linear Convergence of the Randomized Feasible Descent Method Under the Weak Strong Convexity Assumption.
Chenxin MaRachael TappendenMartin TakácPublished in: CoRR (2015)
Keyphrases
- optimization method
- experimental evaluation
- high accuracy
- similarity measure
- significant improvement
- linear model
- preprocessing
- pairwise
- dynamic programming
- computational cost
- synthetic data
- detection method
- image processing
- classification method
- mathematical model
- clustering method
- input data
- classification accuracy
- computational complexity
- computationally efficient
- model selection
- edge detection
- segmentation method
- closed form
- image segmentation
- convergence rate
- learning algorithm
- iterative algorithms