论文标题
在偏见的随机步行，损坏的间隔和对抗设计下学习
On Biased Random Walks, Corrupted Intervals, and Learning Under Adversarial Design
论文作者
论文摘要
我们解决了整数线上损坏的随机过程的概率理论中的一些基本问题。我们分析何时有偏见的随机步行有望达到其底层点，以及何时在自然噪声模型下可以检测到整数点的间隔。我们将这些结果应用于学习阈值和间隔的问题，以在对抗设计下学习的新模型。
We tackle some fundamental problems in probability theory on corrupted random processes on the integer line. We analyze when a biased random walk is expected to reach its bottommost point and when intervals of integer points can be detected under a natural model of noise. We apply these results to problems in learning thresholds and intervals under a new model for learning under adversarial design.
