Faster Stochastic Quasi-Newton Methods

Qingsong Zhang, Feihu Huang, Cheng Deng, Heng Huang

Abstract: Stochastic optimization methods have become a class of popular optimization tools in machine learning. Especially, stochastic gradient descent (SGD) has been widely used for machine learning problems, such as training neural networks, due to low per-iteration computational complexity. In fact, the Newton or quasi-newton (QN) methods leveraging the second-order information are able to achieve a better solution than the first-order methods. Thus, stochastic QN (SQN) methods have been developed to achieve a better solution efficiently than the stochastic first-order methods by utilizing approximate second-order information. However, the existing SQN methods still do not reach the best known stochastic first-order oracle (SFO) complexity. To fill this gap, we propose a novel faster stochastic QN method (SpiderSQN) based on the variance reduced technique of SIPDER. We prove that our SpiderSQN method reaches the best known SFO complexity of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {O}(n+n^{1/2}\epsilon ^{-2})$ </tex-math></inline-formula> in the finite-sum setting to obtain an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\epsilon $ </tex-math></inline-formula> -first-order stationary point. To further improve its practical performance, we incorporate SpiderSQN with different momentum schemes. Moreover, the proposed algorithms are generalized to the online setting, and the corresponding SFO complexity of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {O}(\epsilon ^{-3})$ </tex-math></inline-formula> is developed, which also matches the existing best result. Extensive experiments on benchmark data sets demonstrate that our new algorithms outperform state-of-the-art approaches for nonconvex optimization.