768 citations · 8.4k across the 115 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 10 cited
CoRe Optimizer: An All-in-One Solution for Machine Learning
Marco Eckhoff, Markus Reiher
The optimization algorithm and its hyperparameters can significantly affect the training speed and resulting model accuracy in machine learning applications. The wish list for an i…
cs.LG2023★ 45 cited
Lifelong Machine Learning Potentials
Marco Eckhoff, Markus Reiher
Machine learning potentials (MLPs) trained on accurate quantum chemical data can retain the high accuracy, while inflicting little computational demands. On the downside, they need…