论文标题
差异降低了与加速度的坐标下降：新方法具有令人惊讶的有限和问题的应用
Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems
论文作者
论文摘要
我们提出了随机方差的加速版本减少坐标下降 - ASVRCD。由于其他方差降低了坐标下降方法，例如SEGA或SVRCD，我们的方法可以处理包括不可分离和非平滑正常器的问题，同时仅访问每次迭代中的部分偏导数块。但是，ASVRCD融合了Nesterov的动力，该动力提供了比SEGA和SVRCD的有利的迭代复杂性。作为我们理论的副产品，我们表明Allen-Zhu（2017）的一种变体是ASVRCD的特定情况，为有限的总和恢复了最佳的Oracle复杂性。
We propose an accelerated version of stochastic variance reduced coordinate descent -- ASVRCD. As other variance reduced coordinate descent methods such as SEGA or SVRCD, our method can deal with problems that include a non-separable and non-smooth regularizer, while accessing a random block of partial derivatives in each iteration only. However, ASVRCD incorporates Nesterov's momentum, which offers favorable iteration complexity guarantees over both SEGA and SVRCD. As a by-product of our theory, we show that a variant of Allen-Zhu (2017) is a specific case of ASVRCD, recovering the optimal oracle complexity for the finite sum objective.
