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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use implicit-function learning instead of L2 regression | Regression neural network · High-frequency synthetic regression | test error: at the order of $10^{-1}$ -> at the order of $10^{-2}$ | Improved |
| Use implicit-function learning instead of KDE | Modal regression · Single-circle, double-circle, and high-dimensional double-circle | RMSE | Mixed |
| Use implicit-function learning instead of MDN | Modal regression · Circle datasets | RMSE | Mixed |
| Increase the number of MDN mixture components (ablation) | MDN · Circle datasets | RMSE | No clear effect |
| Add a second-order target-derivative penalty (η=1) (ablation) | Implicit · Unequal-likelihood circle modes | highest-likelihood mode identification | Improved |
| Remove the second-order target-derivative penalty (η=0) (ablation) | Implicit · Unequal-likelihood circle modes | highest-likelihood mode identification | Hurt |
| Use implicit-function learning instead of L2 regression | Regression neural network · Insurance-cost modal regression | RMSE and MAE | Improved |
| Use implicit-function learning instead of MDN | Regression neural network · Bike sharing and Song year | RMSE and MAE | Mixed |
| Increase observation noise | Implicit · High-frequency synthetic regression | test error | Hurt |
| Predict the full local-mode set rather than the global minimum (ablation) | Implicit · Standard regression datasets | prediction error | Hurt |
Closest papers by meaning
- Improving Adaptivity via Over-Parameterization in Sequence Models (NeurIPS 2024 · similarity 0.83)
- ReconBoost: Boosting Can Achieve Modality Reconcilement (ICML 2024 · similarity 0.83)
- Nonparametric Teaching of Implicit Neural Representations (ICML 2024 · similarity 0.82)
- Few-shot Implicit Function Generation via Equivariance (CVPR 2025 · similarity 0.82)
- Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift (ICML 2024 · similarity 0.82)
- Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context (ICML 2024 · similarity 0.82)
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.
