Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking.
Haoran SunSongtao LuMingyi HongPublished in: ICML (2020)
Keyphrases
- convex optimization
- gradient estimation
- interior point methods
- total variation
- norm minimization
- primal dual
- convex optimization problems
- variance reduction
- particle filter
- reinforcement learning
- computational complexity
- video sequences
- mean shift
- object tracking
- kalman filter
- probabilistic model
- particle filtering