arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.07404cs.LGcs.AIstat.ML
收藏

分析超敏感的AI:企业规模机器学习的不稳定性

Analyzing Hypersensitive AI: Instability in Corporate-Scale Machine Learning

OTTO;ITGAIN;Otto Group Solution Provider(奥托集团解决方案提供商)

Michaela Regneri, Malte Hoffmann, Jurij Kost, Niklas Pietsch, Timo Schulz, Sabine Stamm

摘要:

预测几何模型为许多机器学习用例提供了出色的结果。尽管神经预测算法的性能很好,但它们可能会表现出意想不到的不稳定性和方差,特别是在应用于大型数据集时。我们提出了一种方法来衡量几何模型的输出一致性和拓扑稳定性的变化。以word2vec推荐系统为例,分析了单个数据点、近似方法和参数设置对推荐效果的影响。我们的研究结果可以帮助在需要时稳定模型,并在大规模上检测数据点信息价值的差异。

英文摘要:

Predictive geometric models deliver excellent results for many Machine Learning use cases. Despite their undoubted performance, neural predictive algorithms can show unexpected degrees of instability and variance, particularly when applied to large datasets. We present an approach to measure changes in geometric models with respect to both output consistency and topological stability. Considering the example of a recommender system using word2vec, we analyze the influence of single data points, approximation methods and parameter settings. Our findings can help to stabilize models where needed and to detect differences in informational value of data points on a large scale.

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。

↑