Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Inference via $\chi$ Upper Bound Minimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 chiVI instead of BBVI | Bayesian probit regression · Pima | classification error: 0.235 $\pm$ 0.006 -> 0.222 $\pm$ 0.048 | Helped |
| Use chiVI instead of EP | Bayesian probit regression · Ionos | classification error: 0.124 $\pm$ 0.008 -> 0.116 $\pm$ 0.05 | Helped |
| Use chiVI instead of EP | Bayesian probit regression · Madelon | classification error: 0.445 $\pm$ 0.005 -> 0.453 $\pm$ 0.029 | Hurt |
| Use chiVI instead of BBVI | Bayesian probit regression · Covertype | classification error: 0.157 $\pm$ 0.01 -> 0.154 $\pm$ 0.014 | Helped |
| Use chiVI instead of Laplace | Gaussian process classification · Crabs | classification error: 0.02 -> 0.03 $\pm$ 0.03 | Hurt |
| Use chiVI instead of EP | Gaussian process classification · Sonar | classification error: 0.139 -> 0.055 $\pm$ 0.035 | Helped |
| Use chiVI instead of EP | Gaussian process classification · Ionos | classification error: 0.08 $\pm$ 0.04 -> 0.069 $\pm$ 0.034 | Helped |
| Use chiVI instead of BBVI | Cox process posterior uncertainty estimation · Curry | average L1 error: 0.066 -> 0.060 | Helped |
| Use chiVI instead of BBVI | Cox process posterior uncertainty estimation · Demarcus | average L1 error: 0.082 -> 0.073 | Helped |
| Use chiVI instead of BBVI | Cox process posterior uncertainty estimation · Lebron | average L1 error: 0.0812 -> 0.0825 | Hurt |
| Use chiVI instead of BBVI | Cox process posterior uncertainty estimation · Duncan | average L1 error: 0.0871 -> 0.0849 | Helped |
| Minimize the exponentiated CUBO using an unbiased Monte Carlo estimate rather than directly optimizing the biased Monte Carlo CUBO estimate | chiVI optimization · Variational inference | optimization objective bias | Helped |
Closest papers by meaning
- Natural Gradient VI: Guarantees for Non-Conjugate Models (NeurIPS 2025 · similarity 0.89)
- Least squares variational inference (NeurIPS 2025 · similarity 0.89)
- EigenVI: score-based variational inference with orthogonal function expansions (NeurIPS 2024 · similarity 0.89)
- Understanding Stochastic Natural Gradient Variational Inference (ICML 2024 · similarity 0.89)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.89)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.88)
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.