Accelerated Randomized Coordinate Descent Algorithms for Stochastic Optimization and Online Learning
arXiv:1806.01600
Abstract
We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known randomized online coordinate descent algorithms. Furthermore, the proposed algorithms for stochastic optimization exhibit as good convergence rates as the best known randomized coordinate descent algorithms. We also show simulation results to demonstrate performance of the proposed algorithms.
arXiv comment20 pages, 4 figures, 2 tables
References in corpus (6)
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets
- Slow Learners are Fast
- Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling
- Randomized Block Coordinate Descent for Online and Stochastic Optimization
- Randomized Block Subgradient Methods for Convex Nonsmooth and Stochastic Optimization