Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization
arXiv:2003.05482
Abstract
A framework based on iterative coordinate minimization (CM) is developed for stochastic convex optimization. Given that exact coordinate minimization is impossible due to the unknown stochastic nature of the objective function, the crux of the proposed optimization algorithm is an optimal control of the minimization precision in each iteration. We establish the optimal precision control and the resulting order-optimal regret performance for strongly convex and separably nonsmooth functions. An interesting finding is that the optimal progression of precision across iterations is independent of the low-dimensional CM routine employed, suggesting a general framework for extending low-dimensional optimization routines to high-dimensional problems. The proposed algorithm is amenable to online implementation and inherits the scalability and parallelizability properties of CM for large-scale optimization. Requiring only a sublinear order of message exchanges, it also lends itself well to distributed computing as compared with the alternative approach of coordinate gradient descent.
References in corpus (7)
- Parallel Coordinate Descent for L1-Regularized Loss Minimization
- Distributed Coordinate Descent Method for Learning with Big Data
- Distributed Block Coordinate Descent for Minimizing Partially Separable Functions
- Smooth minimization of nonsmooth functions with parallel coordinate descent methods
- On the Finite Time Convergence of Cyclic Coordinate Descent Methods
- Coordinate Descent with Bandit Sampling
- Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization