Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition.
Lukang SunAvetik G. KaragulyanPeter RichtárikPublished in: CoRR (2022)
Keyphrases
- cost function
- objective function
- update rule
- smoothness term
- proximal point algorithm
- sufficient conditions
- image segmentation
- iterative algorithms
- initial conditions
- operator splitting
- convergence speed
- convergence rate
- loss function
- energy functional
- variational methods
- error function
- step size
- faster convergence
- mumford shah functional
- markov random field
- smoothing parameter
- optical flow