Output details
15 - General Engineering
University of Leicester
Article title
Stochastic Optimization on Continuous Domains With Finite-Time Guarantees by Markov Chain Monte Carlo Methods
Type
D - Journal article
Title of journal
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
Article number
-
Volume number
55
Issue number
12
First page of article
2858
ISSN of journal
0018-9286
Year of publication
2010
URL
-
Number of additional authors
2
Additional information
This paper introduces a new approach to the analysis of Markov chain Monte Carlo algorithms for optimization, based on the concepts of finite-time learning from statistical learning theory. The preliminary results of this work were presented as a poster spotlight at NIPS (Neural Information Processing Systems, 2007), a very selective conference in the area of Machine Learning. This paper formed the basis for the successful proposal of the EPSRC project "Optimization with Monte Carlo methods for the control of complex systems" (Ref. EP/H021558/1, PI: A. Lecchini-Visintini).
Interdisciplinary
-
Cross-referral requested
-
Research group
B - Control Systems
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-