arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.02932cs.LGstat.ML
收藏

模式估计的鲁棒性保证及其在抗强盗干扰中的应用

Robustness Guarantees for Mode Estimation with an Application to Bandits

UC Berkeley(加州大学伯克利分校);Google Research(谷歌研究院)

Aldo Pacchiano, Heinrich Jiang, Michael I. Jordan

摘要:

模式估计是统计学中的经典问题,在机器学习中有着广泛的应用。尽管如此,在可能的对抗性数据污染下,对其鲁棒性的理解很少。在本文中,我们给出了精确的鲁棒性保证以及简单随机化下的隐私保证。然后,我们介绍了一个理论,多武装土匪的价值观是模式的奖励分布,而不是平均值。我们证明遗憾的保证顶臂识别,顶M-武器识别,上下文模态土匪,和无限连续武器顶臂恢复的问题。我们在模拟中表明,我们的算法是强大的扰动的武器对抗性噪声序列,从而呈现模态土匪一个有吸引力的选择的情况下,奖励可能有离群值或对抗腐败。

英文摘要:

Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this paper, we give precise robustness guarantees as well as privacy guarantees under simple randomization. We then introduce a theory for multi-armed bandits where the values are the modes of the reward distributions instead of the mean. We prove regret guarantees for the problems of top arm identification, top m-arms identification, contextual modal bandits, and infinite continuous arms top arm recovery. We show in simulations that our algorithms are robust to perturbation of the arms by adversarial noise sequences, thus rendering modal bandits an attractive choice in situations where the rewards may have outliers or adversarial corruptions.

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。

↑