从不可信来源进行鲁棒学习
Robust Learning from Untrusted Sources
摘要:
现代机器学习方法通常需要比单个专家所能提供的更多的数据来进行训练。因此,通过众包等方式从外部来源收集数据已成为标准程序。不幸的是,这些来源的质量并不总是得到保证。作为额外的复杂性,数据可能以分布式方式存储,甚至可能必须保持私有。在这项工作中,我们解决了如何在这种情况下稳健学习的问题。通过统计学习理论的镜头研究这个问题,我们得出了一个程序,允许从所有可用的来源学习,但自动抑制不相关或损坏的数据。我们通过大量的实验表明,我们的方法提供了显着的改进,从强大的统计和分布式优化的替代方法。
英文摘要:
Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality of these sources is not always guaranteed. As additional complications, the data might be stored in a distributed way, or might even have to remain private. In this work, we address the question of how to learn robustly in such scenarios. Studying the problem through the lens of statistical learning theory, we derive a procedure that allows for learning from all available sources, yet automatically suppresses irrelevant or corrupted data. We show by extensive experiments that our method provides significant improvements over alternative approaches from robust statistics and distributed optimization.
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。