ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization
arXiv:1902.05679
Abstract
We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in (Nguyen et al, 2017) and consist of two steps: a proximal gradient and an averaging step making them different from existing nonconvex proximal-type algorithms. The algorithms only require an average smoothness assumption of the nonconvex objective term and additional bounded variance assumption if applied to expectation problems. They work with both constant and adaptive step-sizes, while allowing single sample and mini-batches. In all these cases, we prove that our algorithms can achieve the best-known complexity bounds. One key step of our methods is new constant and adaptive step-sizes that help to achieve desired complexity bounds while improving practical performance. Our constant step-size is much larger than existing methods including proximal SVRG schemes in the single sample case. We also specify the algorithm to the non-composite case that covers existing state-of-the-arts in terms of complexity bounds. Our update also allows one to trade-off between step-sizes and mini-batch sizes to improve performance. We test the proposed algorithms on two composite nonconvex problems and neural networks using several well-known datasets.
45 pages, 8 figures, and 2 table
References in corpus (6)
- Stop Wasting My Gradients: Practical SVRG
- Stochastic Recursive Gradient Algorithm for Nonconvex Optimization
- Neon2: Finding Local Minima via First-Order Oracles
- Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization
- When Does Stochastic Gradient Algorithm Work Well?
- Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
Cited by in corpus (6)
- A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization
- A Stochastic Composite Gradient Method with Incremental Variance Reduction
- On Biased Stochastic Gradient Estimation
- Accelerating Mini-batch SARAH by Step Size Rules
- Variance Reduction on General Adaptive Stochastic Mirror Descent
- Effective Proximal Methods for Non-convex Non-smooth Regularized Learning