AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

On the Estimation of Gaussian Mixture Copula Models

ASHUTOSH TEWARI

ICML 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation

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 identifiability priors (Gaussian priors on the linear constraints of means and second moments) to GMCM likelihood (ablation)GMCM direct likelihood maximization · synthetic 3-D GMC data (Adam, 2000 iterations)recovery of true mean parametersImproved
Replace previous pseudo-EM updates with a correctly derived generalized EM for GMCMGMCM EM estimation · 100 simulated GMC datasetsconverged log-likelihood vs PEM1 and PEM2Improved
Use GMCM instead of GMM (both 40 components)GMCM density estimation · UCI POWER, GAS, HEPMASS, MINIBOONEtest log-likelihoodMixed
Use a numerical root-finding (Chandrupatla) quantile with analytical gradients instead of finite-difference gradientsGMCM likelihood gradient computation · synthetic data, d from 10 to 110CPU time of gradient computation: roughly two orders of magnitude speedupImproved

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