Perturbed Iterate Analysis for Asynchronous Stochastic Optimization
Horia Mania, Xinghao Pan, Dimitris Papailiopoulos et al. · SIAM Journal on Optimization · 2017
We introduce and analyze stochastic optimization methods where the input to each update is perturbed by bounded noise. We show that this framework forms the basis of a unified approach to analyzing asynchronous implementations of stochastic optimization algorithms, by viewing them as serial methods operating on noisy inputs. Using our perturbed iterate framework, we provide new analyses of the Hogwild! algorithm and asynchronous stochastic coordinate descent that are simpler than earlier analyses, remove many assumptions of previous models, and in some cases yield improved upper bounds on the convergence rates. We proceed to apply our framework to develop and analyze KroMagnon: a novel, parallel, sparse stochastic variance-reduced gradient (SVRG) algorithm. We demonstrate experimentally on a 16-core machine that the sparse and parallel version of SVRG is in some cases more than four orders of magnitude faster than the standard SVRG algorithm.
Cited by 154 works. doi:10.1137/16m1057000 Open-access PDF
Authors
References
- Large Scale Distributed Deep Networks
- RCV1: A New Benchmark Collection for Text Categorization Research
- HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
- Distributed asynchronous deterministic and stochastic gradient optimization algorithms
- Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
- Parallelized Stochastic Gradient Descent
- Slow Learners are Fast
- Chaotic relaxation
- Slow Learners are Fast
- Project Adam: building an efficient and scalable deep learning training system