|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
From Infinite to Finite Programs: Explicit Error Bounds with Applications to Approximate Dynamic Programming
If you have a question about this talk, please contact Rachel Furner.
We consider linear programming (LP) problems in infinite dimensional spaces that are in general computationally intractable. Under suitable assumptions, we develop an approximation bridge from the infinite-dimensional LP to tractable finite convex programs in which the performance of the approximation is quantified explicitly. To this end, we adopt the recent developments in two areas of randomized optimization and first order methods, leading to a priori as well as a posterior performance guarantees. We illustrate the generality and implications of our theoretical results in the special case of the long-run average cost and discounted cost optimal control problems for Markov decision processes on Borel spaces. The applicability of the theoretical results is demonstrated through a constrained linear quadratic optimal control problem and a fisheries management problem.
This talk is part of the CCIMI Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsEMBL-EBI Science and Society Programme Faraday Institute Cambridge Area Sequencing Informatics Meeting VI (2014)
Other talksAbundant phased siRNAs in plant reproductive organs Challenging bariatric care practices and fat stigma in ICU RSC Prizewinner's seminar: Self-assembed coordination cages: host-guest chemistry and functional behaviour 'Partisanship, petitioning, and deliberation in British politics, c. 1689-1750' Asylum Monologues Asclepiadaceae