Accelerating Stochastic Composition Optimization
Mengdi Wang, Ji Liu, Ethan Fang
–Neural Information Processing Systems
The popular stochastic gradient methods are well suited for minimizing expected-value objective functions or the sum of a large number of loss functions. Stochastic gradient methods find wide applications in estimation, online learning, and training of deep neural networks.
Neural Information Processing Systems
Nov-21-2025, 08:03:09 GMT