Benchopt
is a package to simplify and make more transparent and reproducible the comparisons of optimization algorithms. The L2-regularized Logistic Regression consists in solving the following program:
$$ \min_w \sum{i=1}^{n} \log(1 + \exp(-y_i x_i^\top w)) + \frac{\lambda}{2} \lVert w \rVert_2^2 $$
where n_samples
) stands for the number of samples, n_features
) stands for the number of features and
This benchmark can be run using the following commands:
pip install -U benchopt
git clone https://github.com/benchopt/benchmark_logreg_l2
benchopt run ./benchmark_logreg_l2
Apart from the problem, options can be passed to benchopt run
, to restrict the benchmarks to some solvers or datasets, e.g.:
$ benchopt run benchmark_logreg_l2 -s sklearn -d simulated --max-runs 10 --n-repetitions 10
Use benchopt run -h
for more details about these options, or visit https://benchopt.github.io/api.html.