Research map / Probabilistic and scientific modeling / Variational and generative sampling
Autoregressive Asymmetric Linear Gaussian Hidden Markov Models
Carlos Puerto-Santana, Pedro Larrañaga, Concha Bielza
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 |
|---|---|---|---|
| add autoregressive terms with state-dependent lags to AsLG-HMM (ablation) | AsLG-HMM · Synthetic scenario 2, sequence 1 | mean BIC: 66074.28 -> 52244.88 | Improved |
| add autoregressive terms to AsLG-HMM (ablation) | AsLG-HMM · Synthetic scenario 1, sequence 1 | mean BIC: 23609.64 -> 23225.69 | Improved |
| add autoregressive terms to AsLG-HMM (ablation) | AsLG-HMM · Beijing air quality | mean BIC: 444813.07 -> 360648.30 | Improved |
| add autoregressive terms to AsLG-HMM (ablation) | AsLG-HMM · Ball-bearing B3 | mean BIC: 217075.67 -> 209120.18 | Improved |
| add context-specific structure learning over naive Bayes (ablation) | Naive-HMM · Synthetic scenario 2, sequence 1 | mean BIC: 66899.60 -> 52244.88 | Improved |
| use mixture emissions (AR-MoG-HMM) instead of asymmetric Gaussian | AR-AsLG-HMM · Synthetic scenario 1, sequence 1 | mean BIC: 22820.08 vs 23225.69 | Hurt |
| use AR-AsLG-HMM instead of AR-MoG-HMM | AR-MoG-HMM · Synthetic scenario 2, sequence 1 | mean BIC: 59343.88 -> 52244.88 | Improved |
| use AR-AsLG-HMM instead of AR-MoG-HMM | AR-MoG-HMM · Beijing air quality | mean BIC: 360648.30 vs 264300.41 | Hurt |
| use AR-AsLG-HMM instead of LMSAR | LMSAR · Ball-bearing B3 | mean BIC: 209120.18 vs 89744.93 | Hurt |
| allow state-dependent variance (AsLG instead of shared variance) | AR-MoG-HMM / LMSAR · Beijing air quality | Viterbi path quality | Improved |
| use AR-AsLG-HMM instead of BMM | BMM · Synthetic scenario 1, sequence 1 | mean BIC: 40413.51 -> 23225.69 | Improved |
Closest papers by meaning
- Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations (ICML 2020 · similarity 0.88)
- Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages (NeurIPS 2016 · similarity 0.86)
- Forward-Backward Latent State Inference for Hidden Continuous-Time semi-Markov Chains (NeurIPS 2022 · similarity 0.86)
- A Spectral Algorithm for Inference in Hidden semi-Markov Models (JMLR 2017 · similarity 0.85)
- Frontiers to the learning of nonparametric hidden Markov models (JMLR 2025 · similarity 0.85)
- State and parameter learning with PARIS particle Gibbs (ICML 2023 · 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.
