Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization

by   Tianyi Chen, et al.

Stochastic compositional optimization generalizes classic (non-compositional) stochastic optimization to the minimization of compositions of functions. Each composition may introduce an additional expectation. The series of expectations may be nested. Stochastic compositional optimization is gaining popularity in applications such as reinforcement learning and meta learning. This paper presents a new Stochastically Corrected Stochastic Compositional gradient method (SCSC). SCSC runs in a single-time scale with a single loop, uses a fixed batch size, and guarantees to converge at the same rate as the stochastic gradient descent (SGD) method for non-compositional stochastic optimization. This is achieved by making a careful improvement to a popular stochastic compositional gradient method. It is easy to apply SGD-improvement techniques to accelerate SCSC. This helps SCSC achieve state-of-the-art performance for stochastic compositional optimization. In particular, we apply Adam to SCSC, and the exhibited rate of convergence matches that of the original Adam on non-compositional stochastic optimization. We test SCSC using the portfolio management and model-agnostic meta-learning tasks.


page 1

page 2

page 3

page 4


A Single-Timescale Stochastic Bilevel Optimization Method

Stochastic bilevel optimization generalizes the classic stochastic optim...

Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems

Stochastic nested optimization, including stochastic compositional, min-...

Riemannian Stochastic Gradient Method for Nested Composition Optimization

This work considers optimization of composition of functions in a nested...

Optimal Design of Queuing Systems via Compositional Stochastic Programming

Well-designed queuing systems form the backbone of modern communications...

Compositional ADAM: An Adaptive Compositional Solver

In this paper, we present C-ADAM, the first adaptive solver for composit...

Biased Stochastic Gradient Descent for Conditional Stochastic Optimization

Conditional Stochastic Optimization (CSO) covers a variety of applicatio...

Sever: A Robust Meta-Algorithm for Stochastic Optimization

In high dimensions, most machine learning methods are brittle to even a ...