Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization
نویسندگان
چکیده
منابع مشابه
A limited memory adaptive trust-region approach for large-scale unconstrained optimization
This study concerns with a trust-region-based method for solving unconstrained optimization problems. The approach takes the advantages of the compact limited memory BFGS updating formula together with an appropriate adaptive radius strategy. In our approach, the adaptive technique leads us to decrease the number of subproblems solving, while utilizing the structure of limited memory quasi-Newt...
متن کاملStochastic Optimization for Large-scale Optimal Transport
Optimal transport (OT) defines a powerful framework to compare probability distributions in a geometrically faithful way. However, the practical impact of OT is still limited because of its computational burden. We propose a new class of stochastic optimization algorithms to cope with large-scale OT problems. These methods can handle arbitrary distributions (either discrete or continuous) as lo...
متن کاملA Three-terms Conjugate Gradient Algorithm for Solving Large-Scale Systems of Nonlinear Equations
Nonlinear conjugate gradient method is well known in solving large-scale unconstrained optimization problems due to it’s low storage requirement and simple to implement. Research activities on it’s application to handle higher dimensional systems of nonlinear equations are just beginning. This paper presents a Threeterm Conjugate Gradient algorithm for solving Large-Scale systems of nonlinear e...
متن کاملA Multilevel Proximal Gradient Algorithm for Large Scale Optimization
Composite optimization models consist of the minimization of the sum of a smooth (not necessarily convex) function and a non-smooth convex function. Such models arise in many applications where, in addition to the composite nature of the objective function, a hierarchy of models is readily available. It is common to take advantage of this hierarchy of models by first solving a low fidelity mode...
متن کاملParallel stochastic gradient algorithms for large-scale matrix completion
This paper develops Jellyfish, an algorithm for solving data-processing problems with matrix-valued decision variables regularized to have low rank. Particular examples of problems solvable by Jellyfish include matrix completion problems and least-squares problems regularized by the nuclear norm or γ2-norm. Jellyfish implements a projected incremental gradient method with a biased, random order...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Knowledge and Data Engineering
سال: 2017
ISSN: 1041-4347
DOI: 10.1109/tkde.2016.2604302