Weikang Qian comments

Repositories
Issues
Comments

Results 13 comments of


                                            Weikang Qian

The loss did not decrease when training on the observations

> interesting! just realized that you set `lamb=0.1` which might be too high, please try what happens with `lamb=0.0`. Still, it doesn't work. As shown at the beginning, changing arguments...

The loss did not decrease when training on the observations

> Could also try `KAN(..., grid_eps=0.02, ...)` which changes KANs to adaptive grids based on sample distribution. > Hi! Were you able to make it work? I'm facing a similar...

The loss did not decrease when training on the observations

> That does sound interesting! However, in my case, MinMax, or MaxAbsScaler did not work. Did you do any other preprocessing apart from using MinMax? It is strange because in...