SpiderBoost: A Class of Faster Variance-reduced Algorithms for Nonconvex Optimization.
Zhe WangKaiyi JiYi ZhouYingbin LiangVahid TarokhPublished in: CoRR (2018)
Keyphrases
- optimization problems
- convex optimization problems
- times faster
- discrete optimization
- computationally demanding
- convex optimization
- evolutionary algorithm
- significant improvement
- machine learning algorithms
- orders of magnitude
- combinatorial optimization
- efficient optimization
- optimization approaches
- optimization method
- highly efficient
- optimization methods
- approximately optimal
- convergence rate
- data structure
- optimization algorithm
- theoretical analysis
- computationally efficient
- worst case
- cost function
- computational complexity