Variance Reduced methods for Non-convex Composition Optimization
It addresses high query complexity in non-convex stochastic composition optimization, an incremental improvement for machine learning practitioners dealing with large-scale problems.
The paper tackles non-convex composition optimization with large inner finite-sum functions, a problem in applications like nonlinear embedding and reinforcement learning, by proposing two variance-reduced algorithms that significantly improve query complexity, with experiments validating the results.
This paper explores the non-convex composition optimization in the form including inner and outer finite-sum functions with a large number of component functions. This problem arises in some important applications such as nonlinear embedding and reinforcement learning. Although existing approaches such as stochastic gradient descent (SGD) and stochastic variance reduced gradient (SVRG) descent can be applied to solve this problem, their query complexity tends to be high, especially when the number of inner component functions is large. In this paper, we apply the variance-reduced technique to derive two variance reduced algorithms that significantly improve the query complexity if the number of inner component functions is large. To the best of our knowledge, this is the first work that establishes the query complexity analysis for non-convex stochastic composition. Experiments validate the proposed algorithms and theoretical analysis.