We prove, under mild conditions, that the stochastic gradient Langevin dynamics converges to a limiting law as time tends to infinity, even in the case where the driving data sequence is dependent.

翻译：在温和的条件下,我们证明,由于时间往往无限,即使驾驶数据序列取决于驾驶数据序列,这种随机的梯度朗埃文动态与限制性法律趋于一致。