@inproceedings{43297b88d2944f4395ae3b0d8771c7a2,
title = "Trade-Offs in Large-Scale Distributed Tuplewise Estimation And Learning",
abstract = "The development of cluster computing frameworks has allowed practitioners to scale out various statistical estimation and machine learning algorithms with minimal programming effort. This is especially true for machine learning problems whose objective function is nicely separable across individual data points, such as classification and regression. In contrast, statistical learning tasks involving pairs (or more generally tuples) of data points---such as metric learning, clustering or ranking---do not lend themselves as easily to data-parallelism and in-memory computing. In this paper, we investigate how to balance between statistical performance and computational efficiency in such distributed tuplewise statistical problems. We first propose a simple strategy based on occasionally repartitioning data across workers between parallel computation stages, where the number of repartitioning steps rules the trade-off between accuracy and runtime. We then present some theoretical results highlighting the benefits brought by the proposed method in terms of variance reduction, and extend our results to design distributed stochastic gradient descent algorithms for tuplewise empirical risk minimization. Our results are supported by numerical experiments in pairwise statistical estimation and learning on synthetic and real-world datasets.",
keywords = "Distributed machine learning, Distributed data processing, U-Statistics, Stochastic gradient descent, AUC optimization",
author = "Robin Vogel and Aur{\'e}lien Bellet and Stephan Cl{\'e}men{\c c}on and Ons Jelassi and Guillaume Papa",
year = "2020",
month = apr,
day = "30",
doi = "10.1007/978-3-030-46147-8_14",
language = "English",
isbn = "978-3-030-46146-1",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "229--245",
editor = "Ulf Brefeld and Elisa Fromont and Andreas Hotho and Arno Knobbe and Marloes Maathuis and C{\'e}line Robardet",
booktitle = "Machine Learning and Knowledge Discovery in Databases",
address = "United Kingdom",
note = "The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2019, ECMLPKDD 2019 ; Conference date: 16-09-2019 Through 20-09-2019",
}