AddTree Covariance Function

dependencies

This project depends on george, numpy, and scipy. george must be compiled manually.

git clone https://github.com/maxc01/george
cd george
python setup.py install

If you are using poetry,

poetry install

examples

synthetic function

cd examples
python addtree_jenatton_small.py

log files will be located in exp_results/addtree/jenatton-small/a-unique-dir. The following figure shows comparison of different algorithms on optimizaing the synthetic function.

model compression

cd examples
python {{ algo }}_model_compression_multiple.py {{ model_name }} OUTPUT_PATH --pretrained PRETRAINED_PATH --prune_epochs 1

model_name can be “vgg16”, “resnet50” or “resnet56”. algo can be “addtree”, “random” , “tpe” or “smac”.

For example, to compress resnet50 using addtree,

python addtree_model_compression_multiple.py resnet50 OUTPUT_PATH --pretrained PRETRAINED_PATH --prune_epochs 1

The following picture shows comparison of different algorithms on compressing resnet50.

citation

@inproceedings{Ma2020a,
  TITLE = {Additive tree-structured covariance function for conditional parameter spaces in {Bayesian} optimization},
  AUTHOR = {Ma, Xingchen and Blaschko, Matthew B.},
  BOOKTITLE = {Artificial Intelligence and Statistics},
  YEAR = {2020},
}