arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1202.3704cs.LGstat.ML
收藏

随机二进制信号的近优目标学习

Near-Optimal Target Learning With Stochastic Binary Signals

Rensselaer Polytechnic Institute(伦斯勒理工学院)

Mithun Chakraborty, Sanmay Das, Malik Magdon-Ismail

摘要:

我们研究学习在一个嘈杂的二分法模型:具体地说,贝叶斯算法来学习一个目标值V只访问噪声实现V是否小于或大于阈值θ。在步骤t = 0,1,2,...,学习者设置阈值θ t并观察符号(V -θ t)的噪声实现。在T个步骤之后,目标是输出在V的η容限内的估计值V。这个问题已经被研究过,主要是在对于符号(V -θ t)的噪声实现具有固定错误概率q < 1/2的环境中。在实际中,经常会出现q可以接近1/2的情况,特别是当θ-> V时,并且很少知道何时会发生这种情况。我们给出了一个伪贝叶斯算法,可证明收敛到V。当真正的先验匹配我们的算法的高斯先验,我们表现出接近最优的预期性能。我们的方法扩展到一般的多阈值设置,其中观察噪声指示k >= 2个区域V属于哪个。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑