论文标题
frugalml：如何更准确，更便宜地使用ML预测API
FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply
论文作者
论文摘要
收费提供的预测API是一个快速增长的行业，也是机器学习作为服务的重要组成部分。尽管有许多此类服务可用，但其价格和性能的异质性使用户确定要用于自己的数据和预算的API或组合的API或组合具有挑战性。我们通过提出FrugalML迈出了解决这一挑战的第一步，该框架共同了解不同数据上每个API的优势，并执行有效的优化，以自动确定最佳的顺序策略，以适应预算约束内可用的API。我们的理论分析表明，可以利用配方中的自然稀疏性，以提高肉豆蔻效应。我们使用Google，Microsoft，Amazon，IBM，BAIDU和其他提供商的ML API进行系统实验，以完成包括面部情感识别，情感分析和语音识别的任务。在各种任务中，Frugalml在匹配最佳单个API的准确性的同时，最多可以降低90％的成本，或者在匹配最佳API成本的同时，高达5％的精度。
Prediction APIs offered for a fee are a fast-growing industry and an important part of machine learning as a service. While many such services are available, the heterogeneity in their price and performance makes it challenging for users to decide which API or combination of APIs to use for their own data and budget. We take a first step towards addressing this challenge by proposing FrugalML, a principled framework that jointly learns the strength and weakness of each API on different data, and performs an efficient optimization to automatically identify the best sequential strategy to adaptively use the available APIs within a budget constraint. Our theoretical analysis shows that natural sparsity in the formulation can be leveraged to make FrugalML efficient. We conduct systematic experiments using ML APIs from Google, Microsoft, Amazon, IBM, Baidu and other providers for tasks including facial emotion recognition, sentiment analysis and speech recognition. Across various tasks, FrugalML can achieve up to 90% cost reduction while matching the accuracy of the best single API, or up to 5% better accuracy while matching the best API's cost.
