Compression-aware training of neural networks using Frank–Wolfe

Chapters in this book

1. Frontmatter I
2. Preface V
3. Acknowledgment VII
4. Contents IX
5. A framework to solve inverse problems for parametric PDEs using adaptive finite elements and neural networks 1
6. Generation of value function data for bilevel optimal control and application to hybrid electric vehicle 17
7. Graph neural networks to predict strokes from blood flow simulations 29
8. Capturing the macroscopic behavior of molecular dynamics with membership functions 41
9. Adaptive gradient-enhanced Gaussian process surrogates for inverse problems 59
10. Multifidelity domain decomposition-based physics-informed neural networks and operators for time-dependent problems 79
11. Constrained piecewise linear optimization by an active signature method 93
12. Parallel trust-region approaches in neural network training 107
13. Trustworthy optimization learning: a brief overview 121
14. Compression-aware training of neural networks using Frank–Wolfe 137
15. Approximation of generalized frequency response functions via vector fitting 169
16. On the nonsmooth regularity condition LIKQ for different abs-normal representations 181
17. Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example 195
18. Index 199