ASAGA:异步并行SAGA
ASAGA: Asynchronous Parallel SAGA
摘要:
我们描述ASAGA,异步并行版本的增量梯度算法SAGA,享有快速的线性收敛速率。通过一个新的视角,我们重新审视并澄清了一个微妙的,但重要的技术问题,目前在很大一部分的异步并行优化算法的收敛速度证明,并提出了一个简化的最近推出的“扰动收敛速度”的框架,解决了它。我们提出了一个40核架构上的实现结果,说明了实际的加速以及硬件开销。
英文摘要:
We describe ASAGA, an asynchronous parallel version of the incremental gradient algorithm SAGA that enjoys fast linear convergence rates. Through a novel perspective, we revisit and clarify a subtle but important technical issue present in a large fraction of the recent convergence rate proofs for asynchronous parallel optimization algorithms, and propose a simplification of the recently introduced "perturbed iterate" framework that resolves it. We thereby prove that ASAGA can obtain a theoretical linear speedup on multi-core systems even without sparsity assumptions. We present results of an implementation on a 40-core architecture illustrating the practical speedup as well as the hardware overhead.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。