NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:7244
Title:Learning nonlinear level sets for dimensionality reduction in function approximation

The paper proposes an interesting dimensionality reduction method for function approximation by generalizing linear level set learning methods to non linear level sets using the RevNet model structure and by introducing a loss function designed to give preference to functions that are sensitive only to few non linear coordinates. The paper is well-written and easy to understand. The methodology is clearly described and the experimental results are convincing. Hence, we recommend acceptance.