Research map / Probabilistic and scientific modeling / Variational and generative sampling
Adaptive Bayesian Sampling with Monte Carlo EM
Anirban Roychowdhury, Srinivasan Parthasarathy
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 |
|---|---|---|---|
| Learn the mass matrix using MCEM | HMC · 1D standard normal | RMSE (μ): 0.0196 -> 0.0115 | Improved |
| Learn the mass matrix using MCEM | SGNHT · 1D standard normal | RMSE (τ): 0.0335 -> 0.0289 | Improved |
| Learn the mass matrix using MCEM | SGHMC · 1D standard normal | RMSE (τ): 0.1646 -> 0.2243 | Hurt |
| Learn the mass matrix using MCEM | HMC · Synthetic Bayesian logistic regression | RMSE (W₀): 0.0456 -> 0.0145 | Improved |
| Learn the mass matrix using MCEM | SG-NPHMC · Synthetic Bayesian logistic regression | RMSE (W₀): 0.4945 -> 0.0990 | Improved |
| Learn the mass matrix using MCEM | SG-NPHMC · Synthetic Bayesian logistic regression | RMSE (W₁): 0.4263 -> 0.4229 | No clear effect |
| Learn the mass matrix using MCEM | SG-NPHMC · 20-Newsgroups | test perplexity: 714 -> 712 | Improved |
| Learn the mass matrix using MCEM | SGNHT · 20-Newsgroups | test perplexity: 757 -> 719 | Improved |
| Learn the mass matrix using MCEM | SGHMC · Reuters | test perplexity: 996 -> 972 | Improved |
| Use the MCEM mass-learning framework instead of the Riemannian sampler | SG-NPHMC · 20-Newsgroups | time per iteration: 0.410s -> 0.049s | Improved |
Closest papers by meaning
- Robust Monte Carlo Sampling using Riemannian Nosé-Poincaré Hamiltonian Dynamics (ICML 2016 · similarity 0.91)
- Transport meets Variational Inference: Controlled Monte Carlo Diffusions (ICLR 2024 · similarity 0.88)
- Sequential Controlled Langevin Diffusions (ICLR 2025 · similarity 0.88)
- Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization (ICML 2025 · similarity 0.87)
- On scalable and efficient training of diffusion samplers (NeurIPS 2025 · similarity 0.87)
- Parallel Affine Transformation Tuning of Markov Chain Monte Carlo (ICML 2024 · 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.
