We analyse an iterative algorithm to minimize quadratic functions whose Hessian matrix $H$ is the expectation of a random symmetric $d\times d$ matrix. The algorithm is a variant of the stochastic variance reduced gradient (SVRG). In several applications, including least-squares regressions, ridge regressions, linear discriminant analysis and regularized linear discriminant analysis, the running time of each iteration is proportional to $d$. Under smoothness and convexity conditions, the algorithm has linear convergence. When applied to quadratic functions, our analysis improves the state-of-the-art performance of SVRG up to a logarithmic factor. Furthermore, for well-conditioned quadratic problems, our analysis improves the state-of-the-art running times of accelerated SVRG, and is better than the known matching lower bound, by a logarithmic factor. Our theoretical results are backed with numerical experiments.
翻译:我们分析一种迭代算法,以最大限度地减少赫森基体的二次函数,赫森基体$H$是随机对称 $d_d_time d$$gml的预期值。该算法是随机对称 $d_d_time d$d_trom。该算法是随机对称 $d_d_time d$$d_trom。该算法是随机对称 $d_timeds d$d_tromax的变异性差降低梯度(SVRG) 。 在几种应用中,包括最小平方回归、脊回归、线性对称分析以及常规的线性线性对立分析,每次迭代的运行时间与美元成正比。 在平滑和共性条件下, 算法具有线性趋近。 当应用对等式函数时, 我们的分析会提高SVRG的状态, 直至对数性系数。此外, 对于条件完善的四方体问题, 我们的分析会改善SVRG的状态, 并且比已知的运行时间比已知的比已知更精确, 。