Research map / Probabilistic and scientific modeling / Variational and generative sampling
Markovian Score Climbing: Variational Inference with KL(p||q)
Christian Naesseth, Fredrik Lindsten, David M. Blei
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 the prior as the proposal instead of the variational approximation (ablation) | MSC · Pima | test error: 0.227\pm 0.046 -> 0.456\pm 0.093 | Hurt |
| use the prior as the proposal instead of the variational approximation (ablation) | MSC · Ionos | test error: 0.117 \pm 0.053 -> 0.182 \pm 0.070 | Hurt |
| use the prior as the proposal instead of the variational approximation (ablation) | MSC · Heart | test error: 0.160 \pm 0.063 -> 0.342 \pm 0.11 | Hurt |
| use MSC rather than self-normalized IS gradients | Bayesian probit regression · Pima, Ionos, and Heart | test error | No clear effect |
| use MSC rather than self-normalized IS gradients | Gaussian approximation to a skew-normal posterior · skew-normal toy model | variational parameter accuracy | Improved |
| use MSC rather than self-normalized IS gradients | Bayesian probit regression · Heart and Ionos | robustness to sample count S | Improved |
| use subset average likelihoods for exchangeable data (ablation) | inclusive-KL VI · exchangeable data | target posterior fidelity | Hurt |
Closest papers by meaning
- Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients (NeurIPS 2022 · similarity 0.91)
- Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics (ICML 2020 · similarity 0.89)
- Variational Inference with Gaussian Score Matching (NeurIPS 2023 · similarity 0.89)
- Marginalized Stochastic Natural Gradients for Black-Box Variational Inference (ICML 2021 · similarity 0.88)
- Kernel Semi-Implicit Variational Inference (ICML 2024 · similarity 0.87)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.87)
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.
