REVIEW 4 cited by
Evaluating Aleatoric Uncertainty via Conditional Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Aleatoric uncertainty quantification seeks for distributional knowledge of random responses, which is important for reliability analysis and robustness improvement in machine learning applications. Previous research on aleatoric uncertainty estimation mainly targets closed-formed conditional densities or variances, which requires strong restrictions on the data distribution or dimensionality. To overcome these restrictions, we study conditional generative models for aleatoric uncertainty estimation. We introduce two metrics to measure the discrepancy between two conditional distributions that suit these models. Both metrics can be easily and unbiasedly computed via Monte Carlo simulation of the conditional generative models, thus facilitating their evaluation and training. We demonstrate numerically how our metrics provide correct measurements of conditional distributional discrepancies and can be used to train conditional models competitive against existing benchmarks.
Forward citations
Cited by 4 Pith papers
-
Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Data
A normalizing flow whose latent variable combines a posterior of a predictive model for the covariate x with a Gaussian nuisance component performs conditional density estimation and supervised dimension reduction for...
-
Optimal Mixture-of-Experts Model Averaging for Conditional Generative Models
Sample-based MMD model averaging of conditional generators is asymptotically optimal, and input-adaptive MoEMA weights improve over fixed averaging and single models across modalities.
-
Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances
Kernel distances on CLaMP3/Aria embeddings score expressive MIDI performances about as well as human listeners and catch contextual corruptions invisible to attribute statistics.
-
Contextual Scenario Generation for Two-Stage Stochastic Programming
Contextual Scenario Generation (CSG) trains a neural mapping from context x to K surrogate scenarios via a distributional MMD loss and a task-based surrogate loss with MMD regularization, enabling fast high-quality 2S...
Discussion (0). Continue with ORCID to comment.