Stochastic gradient method with accelerated stochastic dynamics
نویسنده
چکیده
In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics. A stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is large. The stochasticity of the gradient can be mitigated by the injection of Gaussian noise, which yields the stochastic Langevin gradient method; this method can be used for Bayesian posterior sampling. However, the performance of the stochastic Langevin gradient method depends on the mixing rate of the stochastic dynamics. In this study, we propose violating the detailed balance condition to enhance the mixing rate. Recent studies have revealed that violating the detailed balance condition accelerates the convergence to a stationary state and reduces the correlation time between the samplings. We implement this violation of the detailed balance condition in the stochastic gradient Langevin method and test our method for a simple model to demonstrate its performance.
منابع مشابه
Acceleration and Averaging in Stochastic Descent Dynamics
[1] Nemirovski and Yudin. Problems Complexity and Method Efficiency in Optimization. Wiley-Interscience series in discrete mathematics. Wiley, 1983. [2] W. Krichene, A. Bayen and P. Bartlett. Accelerated Mirror Descent in Continuous and Discrete Time. NIPS 2015. [3] W. Su, S. Boyd and E. Candes. A differential equation for modeling Nesterov's accelerated gradient method: theory and insights. NI...
متن کاملAccelerating Stochastic Gradient Descent
There is widespread sentiment that fast gradient methods (e.g. Nesterov’s acceleration, conjugate gradient, heavy ball) are not effective for the purposes of stochastic optimization due to their instability and error accumulation. Numerous works have attempted to quantify these instabilities in the face of either statistical or non-statistical errors (Paige, 1971; Proakis, 1974; Polyak, 1987; G...
متن کاملStochastic Proximal Gradient Descent with Acceleration Techniques
Proximal gradient descent (PGD) and stochastic proximal gradient descent (SPGD) are popular methods for solving regularized risk minimization problems in machine learning and statistics. In this paper, we propose and analyze an accelerated variant of these methods in the mini-batch setting. This method incorporates two acceleration techniques: one is Nesterov’s acceleration method, and the othe...
متن کاملTwo-stage Stochastic Programing Based on the Accelerated Benders Decomposition for Designing Power Network Design under Uncertainty
In this paper, a comprehensive mathematical model for designing an electric power supply chain network via considering preventive maintenance under risk of network failures is proposed. The risk of capacity disruption of the distribution network is handled via using a two-stage stochastic programming as a framework for modeling the optimization problem. An applied method of planning for the net...
متن کاملAccelerated Stochastic Gradient Method for Composite Regularization
Regularized risk minimization often involves nonsmooth optimization. This can be particularly challenging when the regularizer is a sum of simpler regularizers, as in the overlapping group lasso. Very recently, this is alleviated by using the proximal average, in which an implicitly nonsmooth function is employed to approximate the composite regularizer. In this paper, we propose a novel extens...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1511.06036 شماره
صفحات -
تاریخ انتشار 2015