Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Hidden Markov Models When the Locations of Missing Observations are Unknown
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 HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Synthetic Degree 5, STD 0.5 | accuracy: .66(.15) -> .73(.14) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Synthetic Degree 5, STD 0.75 | accuracy: .52(.17) -> .59(.14) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Synthetic Degree 5, STD 1.0 | accuracy: .49(.18) -> .50(.17) | No clear effect |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Synthetic Degree 3, STD 0.5 | accuracy: .80(.21) -> .84(.16) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Synthetic Degree 3, STD 0.75 | accuracy: .49(.18) -> .73(.15) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Synthetic Degree 3, STD 1.0 | accuracy: .38(5.6) -> .45(5.6) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Multi-Partite, STD 0.5 | accuracy: .69(.16) -> .72(.16) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Multi-Partite, STD 1.0 | accuracy: .48(.18) -> .50(.16) | Helped |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · Multi-Partite, STD 1.5 | accuracy: .40(.17) -> .40(.15) | No clear effect |
| Use HMMOP inference rather than naive prediction on observations with unknown gaps | Sequence labeling with HMMOP · POS | accuracy: .88(.11) -> .89(.12) | No clear effect |
| Use sampling imputation rather than random imputation for unknown omission probabilities | Matching Sampler · Synthetic and semi-synthetic benchmarks | L1 transition-matrix distance | Helped |
| Use the Gaps Sampler rather than the Naive reconstruction | HMM reconstruction with unknown gaps · Correctly specified synthetic and semi-synthetic benchmarks | L1 transition-matrix distance | Helped |
Closest papers by meaning
- Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations (ICML 2020 · similarity 0.87)
- Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages (NeurIPS 2016 · similarity 0.87)
- FlowHMM: Flow-based continuous hidden Markov models (NeurIPS 2022 · similarity 0.86)
- Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling (ICML 2018 · similarity 0.86)
- Inverse Filtering for Hidden Markov Models (NeurIPS 2017 · similarity 0.86)
- Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context (NeurIPS 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.