اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدSeries of convex functions: subdifferential, conjugate and applications to entropy minimization
112
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
A formula for the sub-differential of the sum of a series of convex functions defined on a Banach space was provided by X. Y. Zheng in 1998. In this paper, besides a slight extension to locally convex spaces of Zhengs results, we provide a formula for the conjugate of a countable sum of convex functions. Then we use these results for calculating the sub-differentials and the conjugates in two situations related to entropy minimization, and we study a concrete example met in Statistical Physics.
قيم البحث
اقرأ أيضاً
Entropy functionals (i.e. convex integral functionals) and extensions of these functionals are minimized on convex sets. This paper is aimed at reducing as much as possible the assumptions on the constraint set. Dual equalities and characterizations
of the minimizers are obtained with weak constraint qualifications.
We propose faster methods for unconstrained optimization of emph{structured convex quartics}, which are convex functions of the form begin{equation*} f(x) = c^top x + x^top mathbf{G} x + mathbf{T}[x,x,x] + frac{1}{24} mathopen| mathbf{A} x mathclose|
_4^4 end{equation*} for $c in mathbb{R}^d$, $mathbf{G} in mathbb{R}^{d times d}$, $mathbf{T} in mathbb{R}^{d times d times d}$, and $mathbf{A} in mathbb{R}^{n times d}$ such that $mathbf{A}^top mathbf{A} succ 0$. In particular, we show how to achieve an $epsilon$-optimal minimizer for such functions with only $O(n^{1/5}log^{O(1)}(mathcal{Z}/epsilon))$ calls to a gradient oracle and linear system solver, where $mathcal{Z}$ is a problem-dependent parameter. Our work extends recent ideas on efficient tensor methods and higher-order acceleration techniques to develop a descent method for optimizing the relevant quartic functions. As a natural consequence of our method, we achieve an overall cost of $O(n^{1/5}log^{O(1)}(mathcal{Z} / epsilon))$ calls to a gradient oracle and (sparse) linear system solver for the problem of $ell_4$-regression when $mathbf{A}^top mathbf{A} succ 0$, providing additional insight into what may be achieved for general $ell_p$-regression. Our results show the benefit of combining efficient higher-order methods with recent acceleration techniques for improving convergence rates in fundamental convex optimization problems.
The popular BFGS quasi-Newton minimization algorithm under reasonable conditions converges globally on smooth convex functions. This result was proved by Powell in 1976: we consider its implications for functions that are not smooth. In particular, a
n analogous convergence result holds for functions, like the Euclidean norm, that are nonsmooth at the minimizer.
One revisits the standard saddle-point method based on conjugate duality for solving convex minimization problems. Our aim is to reduce or remove unnecessary topological restrictions on the constraint set. Dual equalities and characterizations of the
minimizers are obtained with weak or without constraint qualifications. The main idea is to work with intrinsic topologies which reflect some geometry of the objective function. The abstract results of this article are applied in other papers to the Monge-Kantorovich optimal transport problem and the minimization of entropy functionals.
We propose a new viewpoint on variational mean-field games with diffusion and quadratic Hamiltonian. We show the equivalence of such mean-field games with a relative entropy minimization at the level of probabilities on curves. We also address the ti
me-discretization of such problems, establish $Gamma$-convergence results as the time step vanishes and propose an efficient algorithm relying on this entropic interpretation as well as on the Sinkhorn scaling algorithm.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
