Choice of regularization

Usually, papers about optimization of GLMs create problem varieties according to regularizations (low-optimal-high).

For example, the papers behind LibLinear first obtain the optimal amount of regularization by cross validation, and focus their benchmarks on timings for those values, then trying out high and low regularizations as varieties (since different solvers have an easier or harder time with more/less regularization).

Example:
https://flore.unifi.it/bitstream/2158/1221395/2/tncg_supplement.pdf

Would be nice to offer a fuller benchmark with more variety of cases beyond just data shapes, with regularization values in particular being one important aspect that affects solver convergence.

The issue does not name specific files or tests. Start by inspecting the benchmark's existing problem-variety and regularization setup, then compare how the current cases are generated. Done should include benchmark cases covering low, cross-validated optimal, and high regularization values in addition to data-shape variation.

Written by the indexing model from the issue text.