2 papers
stat.ML2021
Variable Selection and Regularization via Arbitrary Rectangle-range Generalized Elastic Net
Yujia Ding, Qidi Peng, Zhengming Song +1
We introduce the arbitrary rectangle-range generalized elastic net penalty method, abbreviated to ARGEN, for performing constrained variable selection and regularization in high-di…
cond-mat.mtrl-sci2018
Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
Max Schwarzer, Bryce Rogan, Yadong Ruan +8
We propose a machine learning approach to address a key challenge in materials science: predicting how fractures propagate in brittle materials under stress, and how these material…