In this paper, we proposed a new technique, {\em variance controlled stochastic gradient} (VCSG), to improve the performance of the stochastic variance reduced gradient (SVRG) algorithm. To avoid over-reducing the variance of gradient by SVRG, a hyper-parameter $\lambda$ is introduced in VCSG that is able to control the reduced variance of SVRG. Theory shows that the optimization method can converge by using an unbiased gradient estimator, but in practice, biased gradient estimation can allow more efficient convergence to the vicinity since an unbiased approach is computationally more expensive. $\lambda$ also has the effect of balancing the trade-off between unbiased and biased estimations. Secondly, to minimize the number of full gradient calculations in SVRG, a variance-bounded batch is introduced to reduce the number of gradient calculations required in each iteration. For smooth non-convex functions, the proposed algorithm converges to an approximate first-order stationary point (i.e. $\mathbb{E}\|\nabla{f}(x)\|^{2}\leq\epsilon$) within $\mathcal{O}(min\{1/\epsilon^{3/2},n^{1/4}/\epsilon\})$ number of stochastic gradient evaluations, which improves the leading gradient complexity of stochastic gradient-based method SCS $(\mathcal{O}(min\{1/\epsilon^{5/3},n^{2/3}/\epsilon\})$. It is shown theoretically and experimentally that VCSG can be deployed to improve convergence.
翻译:在本文中,我们提出了一种新的技术, 即 ~ 差异控制 蒸气梯度 { (VCSG ), 来改进随机偏差降低梯度的降低梯度( SVRG) 算法的性能。 为避免SVRG 过度降低梯度差异, 在 VCSG 中引入了超参数$\lambda$\lambda$, 它可以控制SVRG 减少的差异。 理论显示, 优化方法可以通过使用公正的梯度测算仪而趋同, 但在实践中, 有偏差的梯度估计可以更有效地接近附近地区, 因为不偏差的方法在计算上更为复杂。 $lambda$ 也具有平衡公正与偏差估计之间的交易效果。 其次, 为尽量减少SVRGG的完全梯度计算数量, 引入了有差异的批量来减少每升度所需的梯度计算数量。 对于平滑度的功能, 拟议的算法可以集中到一个基础的一级定点( $mathb{ Enabla} ral_ nal_ ral__ } (x_) ral__ ration____ ral_ ration_ = s= s= = s= s==================== =================== = = = = ===== = = = = ========================================xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx