AI Paper Atlas

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

Diminishing Returns Shape Constraints for Interpretability and Regularization

Maya Gupta, Dara Bahri, Andrew Cotter, Kevin Canini

NeurIPS 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 15 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
add convexity constraint (ablation)calibrated linear model · Car SalesTest MSE: 10727 -> 10593Improved
add diminishing-returns shape constraints (ablation)calibrated linear model · Puzzle SalesTest MSE: 8270 -> 8189Improved
add diminishing-returns shape constraints (ablation)RTL · Puzzle SalesTest MSE: 8838 -> 8315Improved
add concavity constraint (ablation)RTL · Domain PricingTest MSE: 0.1109 -> 0.1078Improved
add concavity constraint (ablation)calibrated linear model · Domain PricingTest MSE: 0.1150 -> 0.1120Improved
add concavity constraint (ablation)RTL and calibrated linear · Wine QualityTest MSE: 4.85 -> 4.83No clear effect
add concavity constraint on relatedness (ablation)calibrated linear model · Query-Result Matching (1/10 train)Test MSE: 0.710 -> 0.702Improved
add concavity constraint on relatedness (ablation)calibrated linear model · Query-Result Matching (full train)Test MSE: 0.701 -> 0.722Hurt
add shape constraints (monotonic and concave) over monotonic-only (ablation)RTL · Query-Result Matching (full train)Test MSE: 0.654 -> 0.654No clear effect
add monotonic constraints to unconstrained RTL calibrators (ablation)RTL · Query-Result Matching (full train)Test MSE: 0.639 -> 0.654Hurt
use shape-constrained lattice models instead of unconstrained DNN (ablation)lattice models · Query-Result Matching (1/10 train)Test MSE: test MSE std .002 (RTL) vs 1.69 (DNN)Improved
use SCNN diminishing returns instead of concave-only (ablation)SCNN · Query-Result Matching (1/10 train)Test MSE: 0.673 -> 0.680Hurt

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