PETScML: Second-order solvers for training regression problems in Scientific Machine Learning

arXiv:2403.12188v1 Announce Type: new
Abstract: In recent years, we have witnessed the emergence of scientific machine learning as a data-driven tool for the analysis, by means of deep-learning techniques, of data produced by computational science and engineering applications. At the core of these methods is the supervised training algorithm to learn the neural network realization, a highly non-convex optimization problem that is usually solved using stochastic gradient methods. However, distinct from deep-learning practice, scientific machine-learning training problems feature a much …

abstract algorithm analysis applications arxiv computational core cs.lg cs.ms data data-driven emergence engineering machine machine learning math.oc regression science scientific supervised training tool training type