Preprint
Aug 2026
Tabular Numeric Stretch Transformation
The stretch transformation framework is introduced, which formulates numeric feature preprocessing as an optimization problem to make the target function smoother and thus more learnable and shows that explicitly optimizing for target function smoothness is a powerful and underexplored strategy for tabular deep learnin...
Zihao Ye, Juyong Kim, Johnna Sundberg et al.
· 0 citations