This paper develops a novel passive stochastic gradient algorithm. In passive stochastic approximation, the stochastic gradient algorithm does not have control over the location where noisy gradients of the cost function are evaluated. Classical passive stochastic gradient algorithms use a kernel that approximates a Dirac delta to weigh the gradients based on how far they are evaluated from the desired point. In this paper we construct a multi-kernel passive stochastic gradient algorithm. The algorithm performs substantially better in high dimensional problems and incorporates variance reduction. We analyze the weak convergence of the multi-kernel algorithm and its rate of convergence. In numerical examples, we study the multi-kernel version of the passive least mean squares (LMS) algorithm for transfer learning to compare the performance with the classical passive version.
翻译:本文开发了一个新的被动被动随机梯度算法。 在被动随机近似中, 随机梯度算法无法控制成本函数的噪音梯度评估地点。 经典被动被动随机梯度算法使用一个近似Dirac 三角形的内核来权衡梯度, 根据它们从理想点评估到的距离来权衡梯度。 在本文中, 我们构建了一个多内核被动随机梯度算法。 该算法在高维度问题中表现得要好得多, 并包含差异减少。 我们分析了多内核算法的微弱趋同及其趋同率。 在数字示例中, 我们研究了被动最小正方形(LMS)的多内核方程, 以将学习与典型的被动方位进行比较。