|
MrWhy.com » Videos » Contextual Bandit Algorithms with Supervised Learning Guarantees, incl. discussion by Brendan McMahan |
|
|
Contextual Bandit Algorithms with Supervised Learning Guarantees, incl. discussion by Brendan McMahan
|
Contextual Bandit Algorithms with Supervised Learning Guarantees, incl. discussion by Brendan McMahan
We address the problem of competing with any large set of $N$ policies in the non-stochastic bandit setting, where the learner must repeatedly select among $K$ actions but observes only the reward of the chosen action. We present a modification of the Exp4 algorithm of Auer et al. called Exp4.P, which with high probability incurs regret at most $O(\sqrt{KT\ln N})$. Such a bound does not hold for Exp4 due to the large variance of the importance-weighted estimates used in the algorithm. The new algorithm is tested empirically in a large-scale, real-world dataset. For the stochastic version of the problem, we can use Exp4.P as a subroutine to compete with a possibly infinite set of policies of VC-dimension $d$ while incurring regret at most $ O(\sqrt{Td\ln T})$ with high probability. These guarantees improve on those of all previous algorithms, whether in a stochastic or adversarial environment, and bring us closer to providing guarantees for this setting that are comparable to those in standard supervised learning.
Video Length: 0
Date Found: May 06, 2011
Date Produced: May 06, 2011
View Count: 0
|
|
|
|
|
I got punched by an old guy, for farting near his wife. Read MoreComic book creator Stan Lee talks the future of the medium in the digital age. Panelists Zachary... Read MoreThe U.S. launch of Spotify is still on music lovers' minds. Join Zachary Levi, from NBC’s... Read MoreTuesday: Rupert Murdoch testifies before Parliament on the hacking scandal that brought down "News... Read MoreAfter a long slump, the home construction industry may be showing signs of life. But as Bill... Read More | 1 2 3 4 5 |
|
|
|