2 papers
cs.LG2026
Making Tensor Decoupling More Robust and Less Parametric
Maxime Rochkoulets, Joppe De Jonghe, Mariya Ishteva
Tensor decoupling algorithms recover compact representations of multivariate functions by combining linear factor matrices with univariate internal nonlinearities. We identify two…
cs.LG2026
Robust Basis Spline Decoupling for the Compression of Transformer Models
Joppe De Jonghe, Van Tien Pham, Mariya Ishteva
Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear functions. A single-layer deco…