News for hackers. Stuff that matters.

A comment on When Robustly Tolerable Beats Precariously Optimal.

Re:When Robustly Tolerable Beats Precariously Optimal by grumpyoldfart on Friday March 08, 2024 @05:10AM (#39639650)
It all depends on your the definition of the 'loss' function. One can actually include robustness/sensitivity as the goal and optimize for that.
[ Parent | on HN ]
Re:When Robustly Tolerable Beats Precariously Optimal by Vecr on Friday March 08, 2024 @07:28AM (#39640441)
And run minimax on a cloud of perturbations surrounding each world model, and then weight them together in a tree after that.
[ Parent | on HN ]
Re:When Robustly Tolerable Beats Precariously Optimal by vjerancrnjak on Friday March 08, 2024 @08:55AM (#39641063)
Optimizers are very good. Any "smart" change of the loss function will be equally smartly exploited by the optimizer.

Only way to optimize well is to include the uncertainty of your world model into the model.

For travelling salesman, you obviously want to model that certain roads take longer time to travel at different times of day. No tweak of the loss function would allow you to get realistic/robust solutions to TSP.

[ Parent | on HN ]
Re:When Robustly Tolerable Beats Precariously Optimal by anonymoushn on Friday March 08, 2024 @09:36AM (#39641404)
Why not? Just adding 2SDs to the travel time of each road will get it to try to avoid the roads that get the worst.
[ Parent | on HN ]