AI Paper Atlas

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

An implicit function learning approach for parametric modal regression

Yangchen Pan, Ehsan Imani, Amir-massoud Farahmand, Martha White

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 4 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
Use implicit-function learning instead of L2 regressionRegression neural network · High-frequency synthetic regressiontest error: at the order of $10^{-1}$ -> at the order of $10^{-2}$Improved
Use implicit-function learning instead of KDEModal regression · Single-circle, double-circle, and high-dimensional double-circleRMSEMixed
Use implicit-function learning instead of MDNModal regression · Circle datasetsRMSEMixed
Increase the number of MDN mixture components (ablation)MDN · Circle datasetsRMSENo clear effect
Add a second-order target-derivative penalty (η=1) (ablation)Implicit · Unequal-likelihood circle modeshighest-likelihood mode identificationImproved
Remove the second-order target-derivative penalty (η=0) (ablation)Implicit · Unequal-likelihood circle modeshighest-likelihood mode identificationHurt
Use implicit-function learning instead of L2 regressionRegression neural network · Insurance-cost modal regressionRMSE and MAEImproved
Use implicit-function learning instead of MDNRegression neural network · Bike sharing and Song yearRMSE and MAEMixed
Increase observation noiseImplicit · High-frequency synthetic regressiontest errorHurt
Predict the full local-mode set rather than the global minimum (ablation)Implicit · Standard regression datasetsprediction errorHurt

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