论文标题
在嘈杂的匪徒反馈下学习多类分类器
Learning Multiclass Classifier Under Noisy Bandit Feedback
论文作者
论文摘要
本文解决了多类分类的问题，并涉及嘈杂或嘈杂的匪徒反馈。在这种情况下，学习者可能无法收到真正的反馈。取而代之的是，它收到的反馈已被某些非零概率翻转。我们提出了一种基于公正的估计器技术来处理嘈杂的匪徒反馈的新方法。我们进一步提供了一种可以有效估计噪声速率的方法，从而提供端到端的框架。在高噪声案例中，提出的算法在$ O（\ sqrt {t}）$的顺序中遇到了一个错误，在最坏的情况下，$ O（t^{\ nicefrac {2} {3}}）$的顺序在最坏的情况下。我们使用多个基准数据集上的广泛实验来展示我们的方法的有效性。
This paper addresses the problem of multiclass classification with corrupted or noisy bandit feedback. In this setting, the learner may not receive true feedback. Instead, it receives feedback that has been flipped with some non-zero probability. We propose a novel approach to deal with noisy bandit feedback based on the unbiased estimator technique. We further offer a method that can efficiently estimate the noise rates, thus providing an end-to-end framework. The proposed algorithm enjoys a mistake bound of the order of $O(\sqrt{T})$ in the high noise case and of the order of $O(T^{\nicefrac{2}{3}})$ in the worst case. We show our approach's effectiveness using extensive experiments on several benchmark datasets.
