论文标题
随机BFG的快速线性收敛
Fast Linear Convergence of Randomized BFGS
论文作者
论文摘要
自1950年代后期出现准方法时，它们已成为无限制优化的最广泛使用和有效的算法范式之一。尽管他们取得了巨大的实际成功，但几乎没有理论表明为什么这些方法如此有效。我们为随机BFGS方法提供了半本地收敛速率，该方法可以明显好于梯度下降，最后提供了理论证据，支持该方法的出色经验性能。
Since the late 1950's when quasi-Newton methods first appeared, they have become one of the most widely used and efficient algorithmic paradigms for unconstrained optimization. Despite their immense practical success, there is little theory that shows why these methods are so efficient. We provide a semi-local rate of convergence for the randomized BFGS method which can be significantly better than that of gradient descent, finally giving theoretical evidence supporting the superior empirical performance of the method.
