Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory

arXiv:2404.07170v1 Announce Type: cross
Abstract: This paper leverages the statistics of extreme values to predict the worst-case convergence times of machine learning algorithms. Timing is a critical non-functional property of ML systems, and providing the worst-case converge times is essential to guarantee the availability of ML and its services. However, timing properties such as worst-case convergence times (WCCT) are difficult to verify since (1) they are not encoded in the syntax or semantics of underlying programming languages of AI, (2) …

abstract algorithms arxiv availability case converge convergence cs.ai cs.lg cs.pf cs.pl cs.se functional however machine machine learning machine learning algorithms ml algorithms paper property services statistics systems theory type value values via