A Fast Globally Linearly Convergent Algorithm for the Computation of Wasserstein Barycenters.
Lei YangJia LiDefeng SunKim-Chuan TohPublished in: J. Mach. Learn. Res. (2021)
Keyphrases
- learning algorithm
- computational complexity
- improved algorithm
- expectation maximization
- preprocessing
- np hard
- computationally efficient
- denoising
- times faster
- recognition algorithm
- detection algorithm
- particle swarm optimization
- worst case
- computational cost
- experimental evaluation
- parallel implementation
- high accuracy
- provably convergent
- memory requirements
- experimental study
- k means
- optimal solution
- objective function