Research map / Probabilistic and scientific modeling / Variational and generative sampling
Generalizing Hamiltonian Monte Carlo with Neural Networks
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 learned L2HMC instead of LAHMC | MCMC sampling · 50-d ICG | ESS: 156.6 vs 21.4 | Helped |
| Use learned L2HMC instead of LAHMC | MCMC sampling · Rough Well | ESS: 12.5 vs 8.6 | Helped |
| Use learned L2HMC instead of LAHMC | MCMC sampling · 2-d SCG | ESS: 116 vs 16.7 | Helped |
| Use learned L2HMC instead of LAHMC | MCMC sampling · MoG | ESS: 65.0 vs \ll 0.53 | Helped |
| Use L2HMC instead of HMC | MCMC sampling · SCG | ESS: 106× improvement | Helped |
| Use L2HMC instead of HMC | Latent-variable generative model · MNIST training and held-out data | log-likelihood | Helped |
| Use L2HMC rather than the approximate posterior qψ for posterior sampling | Latent-variable generative model · MNIST block Gibbs inpainting | posterior mode mixing | Helped |
Closest papers by meaning
- Ai-sampler: Adversarial Learning of Markov kernels with involutive maps (ICML 2024 · similarity 0.88)
- Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient (NeurIPS 2024 · similarity 0.88)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · similarity 0.87)
- AutoStep: Locally adaptive involutive MCMC (ICML 2025 · similarity 0.87)
- Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks (ICLR 2025 · similarity 0.87)
- Hamiltonian Score Matching and Generative Flows (NeurIPS 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.