Zobrazeno 1 - 10
of 54
pro vyhledávání: '"David P. Helmbold"'
Publikováno v:
Neural computation. 31(3)
We analyze algorithms for approximating a functionmml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"mml:mrowmml:mif/mml:mimml:mo(/mml:momml:mix/mml:mimml:mo)/mml:momml:mo=/mml:momml:miΦ/mml:mimml:mix/mml:mi/mml:mrow/mml:mathmappingmml:math xmln
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2524cbdff3f299a63fe634fad3f64225
https://pubmed.ncbi.nlm.nih.gov/30645179
https://pubmed.ncbi.nlm.nih.gov/30645179
Publikováno v:
Theoretical Computer Science. 519:29-45
We propose a new way to build a combined list from K base lists, each containing N items. A combined list consists of top segments of various sizes from each base list so that the total size of all top segments equals N. A sequence of item requests i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ce1c7384389606a6ba52e0f0714d1990
https://doi.org/10.1016/j.tcs.2013.09.021
https://doi.org/10.1016/j.tcs.2013.09.021
Publikováno v:
Information and Computation. 269:104453
We study the {0, 1}-loss version of adaptive adversarial multi-armed bandit problems with alpha(>= 1) lossless arms. For the problem, we show a tight bound K - alpha - Theta(1/T) on the minimax expected number of mistakes (1-losses), where K is the n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04aaa09f1d204bbb35bff76badb68cdd
https://doi.org/10.1016/j.ic.2019.104453
https://doi.org/10.1016/j.ic.2019.104453
Publikováno v:
Language and Automata Theory and Applications ISBN: 9783319299990
LATA
LATA
We study the loss version of adversarial multi-armed bandit problems with one lossless arm. We show an adversary’s strategy that forces any player to suffer \(K-1-O(1/T)\) loss where K is the number of arms and T is the number of rounds.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9028befc0be6de32b3e826f617e94e13
https://doi.org/10.1007/978-3-319-30000-9_32
https://doi.org/10.1007/978-3-319-30000-9_32
Autor:
Graham Grindlay, David P. Helmbold
Publikováno v:
Machine Learning. 65:361-387
Trained musicians intuitively produce expressive variations that add to their audience's enjoyment. However, there is little quantitative information about the kinds of strategies used in different musical contexts. Since the literal synthesis of not
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ec0fa58a1b0cb944ac434732e17adb0
https://doi.org/10.1007/s10994-006-8751-3
https://doi.org/10.1007/s10994-006-8751-3
Autor:
David P. Helmbold, Nigel Duffy
Publikováno v:
Machine Learning. 47:153-200
In this paper we examine ensemble methods for regression that leverage or “boost” base regressors by iteratively calling them on modified samples. The most successful leveraging algorithm for classification is AdaBoost, an algorithm that requires
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80b72c3f18dceaebbd7aebbc3513ea8b
https://doi.org/10.1023/a:1013685603443
https://doi.org/10.1023/a:1013685603443
Publikováno v:
Information and Computation. 161:85-139
In the standard on-line model the learning algorithm tries to minimizethe total number of mistakes made in a series of trials. On each trial the learner sees an instance, makes a prediction of its classification, then finds out the correct classifica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::030c27f50e9e2ce628bb34c86a89cea8
https://doi.org/10.1006/inco.2000.2870
https://doi.org/10.1006/inco.2000.2870
Publikováno v:
Mobile Networks and Applications. 5:285-297
We address the problem of deciding when to spin down the disk of a mobile computer in order to extend battery life. One of the most critical resources in mobile computing environments is battery life, and good energy conservation methods increase the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64bc86daf81039947074733c0574b022
https://doi.org/10.1023/a:1019129116852
https://doi.org/10.1023/a:1019129116852
Publikováno v:
IEEE Transactions on Neural Networks. 10:1291-1304
We analyze and compare the well-known gradient descent algorithm and the more recent exponentiated gradient algorithm for training a single neuron with an arbitrary transfer function. Both algorithms are easily generalized to larger neural networks,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2cb37cb656521ef1b48117ab4b63990
https://doi.org/10.1109/72.809075
https://doi.org/10.1109/72.809075
Publikováno v:
Mathematical Finance. 8:325-347
We present an on-line investment algorithm that achieves almost the same wealth as the best constant-rebalanced portfolio determined in hindsight from the actual market outcomes. The algorithm employs a multiplicative update rule derived using a fram
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ef3d813ce9f0c1f412f93255020cca8
https://doi.org/10.1111/1467-9965.00058
https://doi.org/10.1111/1467-9965.00058