Reproducibility in learning
Reproducibility in learning
复制标题
学习的可重复性
DOI:
--
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
Jessica Sorrell
中科院分区:
文献类型:
--
作者:
R. Impagliazzo;Rex Lei;T. Pitassi;Jessica Sorrell
We introduce the notion of a reproducible algorithm in the context of learning. A reproducible learning algorithm is resilient to variations in its samples — with high probability, it returns the exact same output when run on two samples from the same underlying distribution. We begin by unpacking the definition, clarifying how randomness is instrumental in balancing accuracy and reproducibility. We initiate a theory of reproducible algorithms, showing how reproducibility implies desirable properties such as data reuse and efficient testability. Despite the exceedingly strong demand of reproducibility, there are efficient reproducible algorithms for several fundamental problems in statistics and learning. First, we show that any statistical query algorithm can be made reproducible with a modest increase in sample complexity, and we use this to construct reproducible algorithms for finding approximate heavy-hitters and medians. Using these ideas, we give the first reproducible algorithm for learning halfspaces via a reproducible weak learner and a reproducible boosting algorithm. Interestingly, we utilize a connection to foams as a higher-dimension randomized rounding scheme. Finally, we initiate the study of lower bounds and inherent tradeoffs for reproducible algorithms, giving nearly tight sample complexity upper and lower bounds for reproducible versus nonreproducible SQ algorithms.
影响因子:
--
作者:
G. Barthe;Rohit Chadha;Paul Krogmeier;A. Sistla;Mahesh Viswanathan
通讯作者:
G. Barthe;Rohit Chadha;Paul Krogmeier;A. Sistla;Mahesh Viswanathan
影响因子:
1.8
作者:
Albarghouthi, Aws;Hsu, Justin
通讯作者:
Hsu, Justin
DOI:
--
发表时间:
2020
期刊:
Proceedings of Machine Learning Research - COLT
影响因子:
--
作者:
Bun, Mark;Carmosino, Marco;Sorrell, Jessica
通讯作者:
Sorrell, Jessica