Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
Near-Optimal Target Learning With Stochastic Binary Signals
Mithun Chakraborty, Sanmay Das, Malik Magdon-Ismail
We study learning in a noisy bisection model: specifically, Bayesian algorithms to learn a target value V given access only to noisy realizations of whether V is less than or greater than a threshold theta. At step t = 0, 1, 2, ..., the learner sets threshold theta t and observes a noisy realization of sign(V - theta t). After T steps, the goal is to output an estimate V^ which is within an eta-tolerance of V . This problem has been studied, predominantly in environments with a fixed error probability q < 1/2 for the noisy realization of sign(V - theta t). In practice, it is often the case that q can approach 1/2, especially as theta -> V , and there is little known when this happens. We give a pseudo-Bayesian algorithm which provably converges to V. When the true prior matches our algorithm's Gaussian prior, we show near-optimal expected performance. Our methods extend to the general multiple-threshold setting where the observation noisily indicates which of k >= 2 regions V belongs to.
Pages: 69-76
PS Link:
PDF Link: /papers/11/p69-chakraborty.pdf
AUTHOR = "Mithun Chakraborty and Sanmay Das and Malik Magdon-Ismail",
TITLE = "Near-Optimal Target Learning With Stochastic Binary Signals",
BOOKTITLE = "Proceedings of the Twenty-Seventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-11)",
ADDRESS = "Corvallis, Oregon",
YEAR = "2011",
PAGES = "69--76"

hosted by DSL   •   site info   •   help