A machine learning based algorithm selection method to solve the minimum cost flow problem.
Philipp HerrmannAnna MeyerStefan RuzikaLuca E. SchäferFabian von der WarthPublished in: CoRR (2022)
Keyphrases
- optimization algorithm
- high accuracy
- improved algorithm
- detection algorithm
- machine learning
- dynamic programming
- cost function
- significant improvement
- detection method
- synthetic and real images
- selection algorithm
- preprocessing
- experimental evaluation
- learning algorithm
- clustering method
- k means
- fine tuning
- theoretical analysis
- segmentation method
- tree structure
- objective function
- convergence rate
- optimization method
- experimental study
- computational complexity
- em algorithm
- single pass
- matching algorithm
- high efficiency
- estimation algorithm
- computational cost
- mathematical model
- segmentation algorithm
- input data
- computationally efficient
- decomposition method
- classification algorithm
- classification method
- computational efficiency
- expectation maximization
- probabilistic model
- machine learning methods
- energy function
- recognition algorithm
- prior information
- hybrid algorithm
- globally optimal solutions
- selection strategy
- nonlinear integer programming
- search space
- region of interest
- simulated annealing
- reinforcement learning
- support vector machine
- combinatorial optimization
- pairwise
- selection criterion
- active learning
- data mining
- model selection