gg2uah/amortized-optimization-tutorial

Tutorial on amortized optimization for learning to optimize over continuous domains

Tutorial on Amortized Optimization

This repository contains the source code for the paper Tutorial on amortized optimization for learning to optimize over continuous domains by Brandon Amos. The main LaTeX source is in amor.tex and the sphere experiment to generate figure 11 in section 7 is in sphere-exp.py. This also contains the code that generates the following plots:

main-example.py

maxent-animation.py

maxent.py

ctrl.py

imaml.py

fixed-point.py

loss-comp.py

smoothed-loss.py

Licensing

The source code for this tutorial, plots, and sphere experiment is licensed under the CC BY-NC 4.0 License.