It contains links to the paper as well as documentation/slides.
LassoNet sometimes require fine tuning. For optimal performance, consider
- making sure that the initial dense model (with ) has trained well, before starting the LassoNet regularization path. This may involve hyper-parameter tuning, choosing the right optimizer, and so on. If the dense model is underperforming, it is likely that the sparser models will as well.
- making sure the stepsize over the path is not too large. By default, the stepsize runs over the logscale between two values and .