Do, Thang

1. Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation
   2024/10/14 by Do, Thang, S Hannibal, Arnulf Jentzen +2 · 2 citations
   Computer Science · #Stochastic Gradient Optimization Techniques #Neural Networks and Applications #Machine Learning and ELM