In this paper, we study the minimax optimization problem in the smooth and strongly convex-strongly concave setting when we have access to noisy estimates of gradients. In particular, we first analyze the stochastic Gradient Descent Ascent (GDA) method with constant stepsize, and show that it converges to a neighborhood of the solution of the minimax problem. We further provide tight bounds on the convergence rate and the size of this neighborhood. Next, we propose a multistage variant of stochastic GDA (M-GDA) that runs in multiple stages with a particular learning rate decay schedule and converges to the exact solution of the minimax problem. We show M-GDA achieves the lower bounds in terms of noise dependence without any assumptions on the knowledge of noise characteristics. We also show that M-GDA obtains a linear decay rate with respect to the error's dependence on the initial error, although the dependence on condition number is suboptimal. In order to improve this dependence, we apply the multistage machinery to the stochastic Optimistic Gradient Descent Ascent (OGDA) algorithm and propose the M-OGDA algorithm which also achieves the optimal linear decay rate with respect to the initial error. To the best of our knowledge, this method is the first to simultaneously achieve the best dependence on noise characteristic as well as the initial error and condition number.
翻译:在本文中,当我们有机会获得对梯度的杂音估计时,我们研究在平滑和强烈混凝固的细微最大优化环境中的细微最大优化问题。特别是,我们首先以不断的步步化方式分析微散渐渐渐下降源加速度(GDA)方法(GDA),并显示该方法与迷微问题的解决办法相趋近。我们进一步提供了对趋同率和这一附近地区大小的严格界限。接着,我们提议了一个多阶段的Stochectic GDA(M-GDA)变式,该变式在多个阶段,有一个特定的学习速率衰减时间表,与微缩问题的确切解决办法趋同。我们同时显示M-GDA在噪音依赖度方法方面达到了较低的界限,而没有假定对噪音特性特性的了解。我们还表明,M-GDA在错误对初始误差率方面获得了线性衰减率,尽管对条件号的依赖性不尽。为了改进这种依赖性,我们把多阶段机械应用到先诊断式的多位机制,将精准性偏向性差衰变后,并接近于最接近于最精确的ASTentlegradicregradugradegradegradegrademaximal 也提出了最佳的模型,这是最佳的对最佳的测法。