Puzzling Success of Overparameterization: Lottery Tickets or Escape Dimensions?(infoscience.epfl.ch) |
Puzzling Success of Overparameterization: Lottery Tickets or Escape Dimensions?(infoscience.epfl.ch) |
One intuitive way of looking at it is like so - let's say that you have a gaussian-looking plot. You want to fit a gaussian. You have a stupid simple model where you can slide your gaussian left and right.
If your initial starting point happens to be roughly within range, great, your optimizer will take care of it for you and slide it into the correct place. If you're too far, too bad, no meaningful gradient.
Instead, neural nets give you the option to spawn a gaussian anywhere you please. In this case, no sliding is necessary, but it comes at a heavy parametrization cost.
1. Avoid overparameterization by design. Manually create or choose a space of functions that has limited degrees of freedom by construction.
2. Accept overparameterization and regularize.
The latter tends to be more robust, because of the bitter lesson. It's not practical to manually design an ideal, on-demand, just-right limited-parameter model for every dataset we are presented with. The best way to approach that ideal, it turns out, is really to just let the computer figure it out via regularized optimization over an overparameterized space.
Statisticians started moving in favor of overparameterization long before deep learning got off the ground. This trend dates back at least to the machine learning bible, Elements of Statistical Learning (2001).