Robustness, Efficiency, or Privacy: Pick Two in Machine Learning

arXiv:2312.14712v2 Announce Type: replace
Abstract: The success of machine learning (ML) applications relies on vast datasets and distributed architectures which, as they grow, present major challenges. In real-world scenarios, where data often contains sensitive information, issues like data poisoning and hardware failures are common. Ensuring privacy and robustness is vital for the broad adoption of ML in public life. This paper examines the costs associated with achieving these objectives in distributed ML architectures, from both theoretical and empirical perspectives. We …

abstract applications architectures arxiv challenges cs.cr cs.dc cs.lg data data poisoning datasets distributed efficiency hardware information machine machine learning major privacy robustness success type vast vital world