- synthetic, train
- dc, train
- bwsn, test
- bj, train
- synthetic, test
- dc, test
- bwsn, complete
- bj, train
GB-IHT, step size [0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1], trade off [0.0005, 0.001, 0.005, 0.01, 0.05, 0.1], sparsity
GB-GHTP, step size [0.001, 0.005, 0.01, 0.05, 0.1, 0.5, 1], trade off [0.0005, 0.001, 0.005, 0.01, 0.05, 0.1], sparsity, argmin step size, argmin max iteration
BWSN dataset does not take average on multiple randomly generated samples. !!!
DC Beijing use another period data
source /network/rit/lab/ceashpc/fjie/venv/py2/bin/activate cd ~/projects/GraphOpt/block_ghtp/ python evo_dc_exp.py > /network/rit/lab/ceashpc/share_data/GraphOpt/log/ghtp/sparsity=100.txt
Synthetic
BWSN
Washingtong D.C.
Beijing