Towards Stochastic Conjugate Gradient Methods
نویسندگان
چکیده
The method of conjugate gradients provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to stochastic approximation of the gradient. Here we explore a number of ways to adopt ideas from conjugate gradient in the stochastic setting, using fast Hessian-vector products to obtain curvature information cheaply. In our benchmark experiments the resulting highly scalable algorithms converge about an order of magnitude faster than ordinary stochastic gradient descent.
منابع مشابه
Conjugate gradient neural network in prediction of clay behavior and parameters sensitivities
The use of artificial neural networks has increased in many areas of engineering. In particular, this method has been applied to many geotechnical engineering problems and demonstrated some degree of success. A review of the literature reveals that it has been used successfully in modeling soil behavior, site characterization, earth retaining structures, settlement of structures, slope stabilit...
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 کاملAdaptive Stochastic Conjugate Gradient Optimization for Temporal Medical Image Registration
We propose an Adaptive Stochastic Conjugate Gradient (ASCG) optimization algorithm for temporal medical image registration. This method combines the advantages of Conjugate Gradient (CG) method and Adaptive Stochastic Gradient Descent (ASGD) method. The main idea is that the search direction of ASGD is replaced by stochastic approximations of the conjugate gradient of the cost function. In addi...
متن کاملCombining Conjugate Direction Methods with Stochastic Approximation of Gradients
The method of conjugate directions provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to stochastic approximation of the gradient. Here we explore ideas from conjugate gradient in the stochastic (online) setting, using fast Hessian-gradient products to set up low-dimensional Krylov subspaces within indivi...
متن کاملA New Hybrid Conjugate Gradient Method Based on Eigenvalue Analysis for Unconstrained Optimization Problems
In this paper, two extended three-term conjugate gradient methods based on the Liu-Storey ({tt LS}) conjugate gradient method are presented to solve unconstrained optimization problems. A remarkable property of the proposed methods is that the search direction always satisfies the sufficient descent condition independent of line search method, based on eigenvalue analysis. The globa...
متن کامل