Research map / Optimization / Optimizers
Stochastic Gradient MCMC Methods for Hidden Markov Models
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 SG-RLD instead of batch-RLD | HMM inference on ion channel recordings · Ion channel recordings | time to convergence: 1,000 times faster | Helped |
| Use adaptive buffers around sampled subsequences (ablation) | SG-RLD for HMMs · Diagonally dominant synthetic data | 10-step-ahead predictive log probability | Helped |
| Use adaptive buffers around sampled subsequences (ablation) | SG-RLD for HMMs · Reversed cycles synthetic data | 10-step-ahead predictive log probability | Helped |
| Remove buffering (ablation) | SG-RLD for HMMs · Synthetic HMM data | transition matrix estimation | Hurt |
| Treat observations as i.i.d. instead of modeling HMM dynamics (ablation) | SG-RLD · Diagonally dominant and reversed cycles synthetic data | 10-step-ahead predictive log probability | Hurt |
| Use non-conjugate log-normal emissions instead of conjugate Gaussian emissions (ablation) | SG-RLD HMM · Synthetic log-normal emission data | transition matrix estimation convergence | Helped |
| Use non-conjugate log-normal emissions instead of conjugate Gaussian emissions (ablation) | SG-RLD HMM · Synthetic log-normal emission data | number of states selected: 2; 4 | Helped |
Closest papers by meaning
- Structured Stochastic Gradient MCMC (ICML 2022 · similarity 0.92)
- Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo (NeurIPS 2016 · similarity 0.90)
- Communication-Efficient Stochastic Gradient MCMC for Neural Networks (AAAI 2019 · similarity 0.90)
- High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models (AAAI 2016 · similarity 0.89)
- Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo (ICLR 2025 · similarity 0.88)
- Learning to Explore for Stochastic Gradient MCMC (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.