Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Borkar , VS"'
Autor:
BORKAR, VS, JAIN, AV
Publikováno v:
IndraStra Global.
Using the expression for the unnormalized nonlinear filter for a hidden Markov model, we develop a dynamic-programming-like backward recursion for the filter. This is combined with some ideas from reinforcement learning and a conditional version of i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=issn23813652::be6221b09e946eb50a21254a662a9353
Autor:
Borkar, VS, Meyn, SP
It is shown here that stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergence of the algorithm. Several specific classes of algorithms are consid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d7b411ad1cf3766d34be3ad368eaa07e
http://eprints.iisc.ernet.in/1737/
http://eprints.iisc.ernet.in/1737/
Autor:
Soumyanath, K, Borkar, VS
In a companion paper [6] we presented theoretical analysis of an analog network for fixed-point computation. This paper applies these results to several applications from numerical analysis and combinatorial optimization, in particular: 1) solving sy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::879ed466ba8be9c1783ac37ffa75f6d6
http://eprints.iisc.ernet.in/1565/
http://eprints.iisc.ernet.in/1565/
Autor:
Borkar, VS, Mitter, SK
Publikováno v:
IndraStra Global.
The constant stepsize analog of Gelfand-Mitter type discrete-time stochastic recursive algorithms is shown to track an associated stochastic differential equation in the strong sense, i.e., with respect to an appropriate divergence measure.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=issn23813652::884b40fb4c4ca507ad39ab1ff16dc677
http://eprints.iisc.ac.in/18011/1/fulltext.pdf
http://eprints.iisc.ac.in/18011/1/fulltext.pdf
Autor:
Borkar, VS
Publikováno v:
IndraStra Global.
The ergodic or long-run average cost control problem for a partially observed finite-state Markov chain is studied via the associated fully observed separated control problem for the nonlinear filter. Dynamic programming equations for the latter are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=issn23813652::11d62f42b9935721ec1a997aa6ed3f25
https://igi.indrastra.com/items/show/187654
https://igi.indrastra.com/items/show/187654
Autor:
Borkar, VS, Meyn, SP
It is shown that the stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergence of the algorithm. Several specific classes of algorithms are conside
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ef591d1ccddce77542cc0bc7d47a294b
http://eprints.iisc.ac.in/6096/
http://eprints.iisc.ac.in/6096/
Publikováno v:
IndraStra Global.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1b3ef79d8efb3302d78378a093adbd46
https://igi.indrastra.com/items/show/196565
https://igi.indrastra.com/items/show/196565
Autor:
Borkar, VS
Publikováno v:
IndraStra Global.
The distributed implementation of an algorithm for computing fixed points of an infinity-nonexpansive map is shown to converge to the set of fixed points under very general conditions.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b8e3addc2b5966f1f8d60522f41e5e83
http://eprints.iisc.ac.in/37115/1/Distributed_computation.pdf
http://eprints.iisc.ac.in/37115/1/Distributed_computation.pdf
Autor:
Borkar , VS, Phansalkar, VV
For a class of distributed recursive algorithms, it is shown that a stochastic approximation-like tapering stepsize routine suppresses the effects of interprocessor delays.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::195c15a93bf8f09413230873eb1d4dc7
http://eprints.iisc.ernet.in/36630/
http://eprints.iisc.ernet.in/36630/
Autor:
Borkar, VS
Publikováno v:
IndraStra Global.
The problem of controlling a Markov chain on a countable state space with ergodic or ’long run average’ cost is studied in the presence of additional constraints, requiring finitely many (say, m) other ergodic costs to satisfy prescribed bounds.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=issn23813652::504a115c71f1b93309ae4174d1f017de
http://eprints.iisc.ac.in/7889/1/ERGODIC_CONTROL-153.pdf
http://eprints.iisc.ac.in/7889/1/ERGODIC_CONTROL-153.pdf