Research map / Probabilistic and scientific modeling / Variational and generative sampling
Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning
Rui Luo, Jianhong Wang, Yaodong Yang, Jun WANG, Zhanxing Zhu
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 TACT-HMC instead of the strongest reported baseline | MLP classification · EMNIST Balanced, 0%, 20%, and 30% permuted labels | accuracy: 84.53% -> 84.85%; 82.64% -> 82.95%; 81.70% -> 81.77% | Improved |
| Use TACT-HMC instead of the strongest reported baseline | RNN classification · Fashion-MNIST, 0%, 20%, and 30% permuted labels | accuracy: 90.25% -> 90.84%; 88.91% -> 89.61%; 88.58% -> 89.01% | Improved |
| Use TACT-HMC instead of the strongest reported baseline | CNN classification · CIFAR-10, 0%, 20%, and 30% permuted labels | accuracy: 76.60% -> 78.93%; 73.87% -> 74.88%; 71.79% -> 73.22% | Improved |
| Remove continuous tempering while retaining thermostats (ablation) | TACT-HMC · Synthetic multimodal distributions with noisy gradients | sampling coverage | Hurt |
| Remove thermostatting while retaining tempering (ablation) | TACT-HMC · Synthetic multimodal distributions with noisy gradients | sampling accuracy | Hurt |
| Use TACT-HMC rather than SGHMC | TACT-HMC · 1D Gaussian mixture | effective sample size (ESS): 2.1096×10^4; roughly 60.2% of the value for SGHMC | Hurt |
| Use TACT-HMC rather than SGNHT | TACT-HMC · 1D Gaussian mixture | effective sample size (ESS): 2.1096×10^4; 50.9% of that for SGNHT | Hurt |
Closest papers by meaning
- Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks (NeurIPS 2017 · similarity 0.88)
- Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling (NeurIPS 2021 · similarity 0.88)
- Adaptive Bayesian Sampling with Monte Carlo EM (NeurIPS 2017 · similarity 0.88)
- Accelerated Parallel Tempering via Neural Transports (ICLR 2026 · similarity 0.88)
- Generalizing Hamiltonian Monte Carlo with Neural Networks (ICLR 2018 · similarity 0.87)
- Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks (ICLR 2025 · similarity 0.85)
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.
