AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Learning nonlinear level sets for dimensionality reduction in function approximation

Guannan Zhang, Jiaxin Zhang, Jacob Hinkle

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
NLL nonlinear transformation instead of no transformation (brute-force NN), 500 samples20+20 NN · f4validation relative RMSE: 61.22% -> 13.41%Improved
NLL instead of AS, 500 samples20+20 NN · f4validation relative RMSE: 65.98% -> 13.41%Improved
NLL instead of SIR, 500 samples20+20 NN · f5validation relative RMSE: 28.17% -> 13.36%Improved
NLL with small network (1 hidden layer, 10 neurons), 10,000 samples1x10 NN · f4validation relative RMSE: 30.36% -> 3.11%Improved
NLL with small network, 10,000 samples1x10 NN · f5validation relative RMSE: 16.32% -> 6.74%Improved
NLL with 100 training samples20+20 NN · f4validation relative RMSE: 96.74% -> 98.23%No clear effect
NLL with 100 training samples20+20 NN · f5validation relative RMSE: 40.95% -> 77.79%No clear effect
NLL with 10,000 training samples (large data)20+20 NN · f5validation relative RMSE: 3.56% -> 3.04%No clear effect
NLL for composite shell, 500 samples1x20 NN · composite shellvalidation relative RMSE: 67.57% -> 11.96%Improved
NLL for composite shell, 100 samples1x20 NN · composite shellvalidation relative RMSE: 65.74% -> 63.18%No clear effect
NLL reduces sensitivity of inactive dimension Dim 4 vs ASNLL · composite shellrelative sensitivity: 0.20 -> 0.011Improved
NLL vs AS/SIR on sensitivity of inactive dimensions (20D functions)NLL · f4, f5relative sensitivityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy