A theoretical and empirical study of new adaptive algorithms with additional momentum steps and shifted updates for stochastic non-convex optimization.
Cristian Daniel AlecsaPublished in: CoRR (2021)
Keyphrases
- convex optimization
- adaptive algorithms
- theoretical and empirical study
- non stationary
- swarm intelligence
- interior point methods
- total variation
- low rank
- norm minimization
- convex optimization problems
- primal dual
- feature vectors
- convex formulation
- convex relaxation
- machine learning
- particle swarm optimization
- semidefinite program
- operator splitting
- feature extraction