Research map / Probabilistic and scientific modeling / Variational and generative sampling
A Contrastive Divergence for Combining Variational Inference and MCMC
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 |
|---|---|---|---|
| Optimize the amortized variational parameters with VCD instead of Standard KL | Bayesian logistic matrix factorization · MNIST | average test log-likelihood: -111.20 -> -101.26 | Helped |
| Optimize the amortized variational parameters with VCD instead of Amortized MCMC | Bayesian logistic matrix factorization · MNIST | average test log-likelihood: -103.61 -> -101.26 | Helped |
| Optimize the amortized variational parameters with VCD instead of Standard KL | Bayesian logistic matrix factorization · Fashion-MNIST | average test log-likelihood: -127.43 -> -121.11 | Helped |
| Optimize the amortized variational parameters with VCD instead of Amortized MCMC | Bayesian logistic matrix factorization · Fashion-MNIST | average test log-likelihood: -121.86 -> -121.11 | Helped |
| Optimize the amortized variational parameters with VCD instead of Standard KL | VAE · MNIST | average test log-likelihood: -98.46 -> -95.86 | Helped |
| Optimize the amortized variational parameters with VCD instead of Amortized MCMC | VAE · MNIST | average test log-likelihood: -96.23 -> -95.86 | Helped |
| Optimize the amortized variational parameters with VCD instead of Standard KL | VAE · Fashion-MNIST | average test log-likelihood: -124.63 -> -117.65 | Helped |
| Optimize the amortized variational parameters with VCD instead of Amortized MCMC | VAE · Fashion-MNIST | average test log-likelihood: -117.74 -> -117.65 | Helped |
| Increase the number of HMC steps | VCD-trained VAE · MNIST and Fashion-MNIST | average test log-likelihood | Helped |
Closest papers by meaning
- SoftCVI: Contrastive variational inference with self-generated soft labels (ICLR 2025 · similarity 0.91)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.90)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.90)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.90)
- Online Variational Sequential Monte Carlo (ICML 2024 · similarity 0.88)
- Forward $\chi^2$ Divergence Based Variational Importance Sampling (ICLR 2024 · 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.