A Nearly-Linear Time Algorithm for Structured Support Vector Machines.
Yuzhou GuZhao SongLichen ZhangPublished in: CoRR (2023)
Keyphrases
- worst case
- matching algorithm
- computational complexity
- improved algorithm
- experimental evaluation
- optimal solution
- dynamic programming
- optimization algorithm
- support vector
- learning algorithm
- k means
- preprocessing
- objective function
- simulated annealing
- input data
- multi class classification
- cost function
- computational cost
- times faster
- similarity measure
- linear programming
- detection algorithm
- clustering method
- maximum margin
- structured data
- machine learning
- support vector machine svm
- theoretical analysis
- computationally efficient
- expectation maximization
- particle swarm optimization
- high accuracy
- classification accuracy
- np hard
- multi objective
- significant improvement