Geometric Descent Method for Convex Composite Minimization
نویسندگان
چکیده
In this paper, we extend the geometric descent method recently proposed by Bubeck, Lee and Singh [5] to solving nonsmooth and strongly convex composite problems. We prove that the resulting algorithm, GeoPG, converges with a linear rate (1− 1/√κ), thus achieves the optimal rate among first-order methods, where κ is the condition number of the problem. Numerical results on linear regression and logistic regression with elastic net regularization show that GeoPG compares favorably with Nesterov’s accelerated proximal gradient method, especially when the problem is ill-conditioned.
منابع مشابه
UniVR: A Universal Variance Reduction Framework for Proximal Stochastic Gradient Method
We revisit an important class of composite stochastic minimization problems that often arises from empirical risk minimization settings, such as Lasso, Ridge Regression, and Logistic Regression. We present a new algorithm UniVR based on stochastic gradient descent with variance reduction. Our algorithm supports non-strongly convex objectives directly, and outperforms all of the state-of-the-art...
متن کاملAn Accelerated Proximal Coordinate Gradient Method
We develop an accelerated randomized proximal coordinate gradient (APCG) method, for solving a broad class of composite convex optimization problems. In particular, our method achieves faster linear convergence rates for minimizing strongly convex functions than existing randomized proximal coordinate gradient methods. We show how to apply the APCG method to solve the dual of the regularized em...
متن کاملSupplementary Material: Geometric Descent Method for Convex Composite Minimization
We argue that the geometric intuition of GeoPG is still clear. Note that we are still constructing two balls that contain x∗ and shrink at the same absolute amount. In GeoPG, since we assume that the smooth function f is strongly convex, we naturally have one ball that contains x∗, and this ball is related to the proximal gradient Gt, instead of the gradient due to the presence of the nonsmooth...
متن کاملRandomized Block Coordinate Descent for Online and Stochastic Optimization
Two types of low cost-per-iteration gradient descent methods have been extensively studied in parallel. One is online or stochastic gradient descent ( OGD/SGD), and the other is randomzied coordinate descent (RBCD). In this paper, we combine the two types of methods together and propose online randomized block coordinate descent (ORBCD). At each iteration, ORBCD only computes the partial gradie...
متن کاملRandomized block proximal damped Newton method for composite self-concordant minimization
In this paper we consider the composite self-concordant (CSC) minimization problem, which minimizes the sum of a self-concordant function f and a (possibly nonsmooth) proper closed convex function g. The CSC minimization is the cornerstone of the path-following interior point methods for solving a broad class of convex optimization problems. It has also found numerous applications in machine le...
متن کامل