NDLI: A stochastic gradient type algorithm for closed-loop problems

Content Provider	Springer Nature Link
Author	Roy, Jean Sébastien Barty, Kengy Strugarek, Cyrille
Copyright Year	2007
Abstract	We focus on the numerical solution of closed-loop stochastic problems, and propose a perturbed gradient algorithm to achieve this goal. The main hurdle in such problems is the fact that the control variables are infinite-dimensional, due to, e.g., the information constraints. Alternatively said, control variables are feedbacks, i.e., functions. Such controls have hence to be represented in a finite way in order to solve the problem numerically. In the same way, the gradient of the criterion is itself an infinite-dimensional object. Our algorithm replaces this exact (and unknown) gradient by a perturbed one, which consists of the product of the true gradient evaluated at a random point and a kernel function which extends this gradient to the neighbourhood of the random point. Proceeding this way, we explore the whole space iteration after iteration through random points. Since each kernel function is perfectly known by a small number of parameters, say N, the control at iteration k is perfectly known as an infinite-dimensional object by at most N × k parameters. The main strength of this method is that it avoids any discretization of the underlying space, provided that we can sample as many points as needed in this space. Moreover, our algorithm can take into account the possible measurability constraints of the problem in a new way. Finally, the randomized strategy implemented by the algorithm causes the most probable parts of the space to be the most explored ones, which is a priori an interesting feature. In this paper, we first prove two convergence results of this algorithm in the strongly convex and convex cases, and then give some numerical examples showing the interest of this method for practical stochastic optimization problems.
Ending Page	78
Page Count	28
Starting Page	51
File Format	PDF
ISSN	00255610
e-ISSN	14364646
Journal	Mathematical Programming
Issue Number	1
Volume Number	119
Language	English
Publisher	Springer-Verlag
Publisher Date	2007-11-29
Publisher Place	Berlin, Heidelberg
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Mathematical Methods in Physics Closed-loop problems Stochastic quasi-gradient Mathematics of Computing Calculus of Variations and Optimal Control; Optimization Optimal stochastic control Mathematical and Computational Physics Numerical Analysis Perturbed gradient Stochastic learning and adaptive control Stochastic approximation Combinatorics
Content Type	Text
Resource Type	Article
Subject	Mathematics Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm

Computational complexity of stochastic programming problems

Erratum to: Computational complexity of stochastic programming problems

Accelerated gradient methods for nonconvex nonlinear and stochastic programming

Tractable Approximations to Robust Conic Optimization Problems

A 3/2-approximation algorithm for some minimum-cost graph problems

Pegasos: primal estimated sub-gradient solver for SVM

Power optimization for connectivity problems

An optimal adaptive algorithm for the approximation of concave functions

A stochastic gradient type algorithm for closed-loop problems

Similar Documents

Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm

Computational complexity of stochastic programming problems

Erratum to: Computational complexity of stochastic programming problems

Accelerated gradient methods for nonconvex nonlinear and stochastic programming

Tractable Approximations to Robust Conic Optimization Problems

A 3/2-approximation algorithm for some minimum-cost graph problems

Pegasos: primal estimated sub-gradient solver for SVM

Power optimization for connectivity problems

An optimal adaptive algorithm for the approximation of concave functions

A stochastic gradient type algorithm for closed-loop problems