On the SDEs and Scaling Rules for Adaptive Gradient Algorithms.
Sadhika MalladiKaifeng LyuAbhishek PanigrahiSanjeev AroraPublished in: CoRR (2022)
Keyphrases
- recursive least squares
- decision rules
- computational efficiency
- neural network
- logic programs
- black box
- computationally expensive
- orders of magnitude
- benchmark datasets
- computationally efficient
- worst case
- knowledge discovery
- computational cost
- evolutionary algorithm
- computational complexity
- data structure
- social networks