Search Results for author:
Found 4 papers, 3 papers with code
Physics-Informed Learning of Aerosol Microphysics
The original M7 model is used to generate data of input-output pairs to train a neural network on it.
Scalable Hyperparameter Optimization with Lazy Gaussian Processes
Reducing its computational complexity from cubic to quadratic allows an efficient strong scaling of Bayesian Optimization while outperforming the previous approach regarding optimization accuracy.
GradVis: Visualization and Second Order Analysis of Optimization Surfaces during the Training of Deep Neural Networks
Current training methods for deep neural networks boil down to very high dimensional and non-convex optimization problems which are usually solved by a wide range of stochastic gradient descent methods.
High-Performance Derivative Computations using CoDiPack
Especially for Jacobi taping, recent advances by using expression templates make this approach very attractive for large scale software.
Mathematical Software 68N30 G.1.4; G.4; D.2.2
