Improved Algorithms for Convex Minimization in Relative Scale
نویسنده
چکیده
In this paper we propose two modifications to Nesterov’s algorithms for minimizing convex functions in relative scale. The first is based on a bisection technique and leads to improved theoretical iteration complexity and the second is a heuristic for avoiding restarting behavior. The fastest of our algorithms produces a solution within relative error O(1/k) of the optimum, with k being the iteration counter.
منابع مشابه
Unconstrained Convex Minimization in Relative Scale
In this paper we present a new approach to constructing schemes for unconstrained convex minimization, which compute approximate solutions with a certain relative accuracy. This approach is based on a special conic model of the unconstrained minimization problem. Using a structural model of the objective function we can employ the efficient smoothing technique. The fastest of our algorithms sol...
متن کاملSDO relaxation approach to fractional quadratic minimization with one quadratic constraint
In this paper, we study the problem of minimizing the ratio of two quadratic functions subject to a quadratic constraint. First we introduce a parametric equivalent of the problem. Then a bisection and a generalized Newton-based method algorithms are presented to solve it. In order to solve the quadratically constrained quadratic minimization problem within both algorithms, a semidefinite optim...
متن کاملSome Algorithms for Large-scale Linear and Convex Minimization in Relative Scale
This thesis is concerned with the study of algorithms for approximately solving large-scale linear and nonsmooth convex minimization problems within a prescribed relative error δ of the optimum. The methods we propose converge in O(1/δ 2) or O(1/δ) iterations of a first-order type. While the theoretical lower iteration bound for approximately solving (in the absolute sense) nonsmooth convex min...
متن کاملStochastic Majorization-Minimization Algorithms for Large-Scale Optimization
Majorization-minimization algorithms consist of iteratively minimizing a majorizing surrogate of an objective function. Because of its simplicity and its wide applicability, this principle has been very popular in statistics and in signal processing. In this paper, we intend to make this principle scalable. We introduce a stochastic majorization-minimization scheme which is able to deal with la...
متن کاملA Projected Alternating Least square Approach for Computation of Nonnegative Matrix Factorization
Nonnegative matrix factorization (NMF) is a common method in data mining that have been used in different applications as a dimension reduction, classification or clustering method. Methods in alternating least square (ALS) approach usually used to solve this non-convex minimization problem. At each step of ALS algorithms two convex least square problems should be solved, which causes high com...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- SIAM Journal on Optimization
دوره 21 شماره
صفحات -
تاریخ انتشار 2011