A Bregman Forward-Backward Linesearch Algorithm for Nonconvex Composite Optimization: Superlinear Convergence to Nonisolated Local Minima
نویسندگان
چکیده
A Bregman Forward-Backward Linesearch Algorithm for Nonconvex Composite Optimization: Superlinear Convergence to Nonisolated Local Minima
منابع مشابه
Finding Approximate Local Minima for Nonconvex Optimization in Linear Time
We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which is linear in the input representation. The previously fastest methods run in time proportional to matrix inversion or worse. The time complexity of our algorithm to find a local minimum is even faster than that of gradient descent to find a critical point (which can...
متن کاملGlobal Convergence of Splitting Methods for Nonconvex Composite Optimization
We consider the problem of minimizing the sum of a smooth function h with a bounded Hessian, and a nonsmooth function. We assume that the latter function is a composition of a proper closed function P and a surjective linear map M, with the proximal mappings of τP , τ > 0, simple to compute. This problem is nonconvex in general and encompasses many important applications in engineering and mach...
متن کاملAlmost sure convergence of the forward-backward-forward splitting algorithm
In this paper, we propose a stochastic forward–backward–forward splitting algorithm and prove its almost sure weak convergence in real separable Hilbert spaces. Applications to composite monotone inclusion andminimization problems are demonstrated.
متن کاملNonconvex optimization using negative curvature within a modified linesearch
This paper describes a new algorithm for the solution of nonconvex unconstrained optimization problems, with the property of converging to points satisfying second-order necessary optimality conditions. The algorithm is based on a procedure which, from two descent directions, a Newton-type direction and a direction of negative curvature, selects in each iteration the linesearch model best adapt...
متن کاملLocal Convergence of Sequential Convex Programming for Nonconvex Optimization
where c ∈ R, g : R → R is non-linear and smooth on its domain, and Ω is a nonempty closed convex subset in R. This paper introduces sequential convex programming (SCP), a local optimization method for solving the nonconvex problem (P). We prove that under acceptable assumptions the SCP method locally converges to a KKT point of (P) and the rate of convergence is linear. Problems in the form of ...
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: Siam Journal on Optimization
سال: 2021
ISSN: ['1095-7189', '1052-6234']
DOI: https://doi.org/10.1137/19m1264783