论文信息 - Convergence Analysis of Optimization Algorithms

Convergence Analysis of Optimization Algorithms

The regret bound of an optimization algorithms is one of the basic criteria for evaluating the performance of the given algorithm. By inspecting the differences between the regret bounds of traditional algorithms and adaptive one, we provide a guide for choosing an optimizer with respect to the given data set and the loss function. For analysis, we assume that the loss function is convex and its gradient is Lipschitz continuous.

[1] Tianbao Yang,et al. Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization , 2016, 1604.03257.

[2] Matthew D. Zeiler. ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[3] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4] Euhanna Ghadimi,et al. Global convergence of the Heavy-ball method for convex optimization , 2014, 2015 European Control Conference (ECC).

[5] Sebastian Ruder,et al. An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[6] Nathan Srebro,et al. The Marginal Value of Adaptive Gradient Methods in Machine Learning , 2017, NIPS.

[7] Yurii Nesterov,et al. Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.