Research map / Probabilistic and scientific modeling / Variational and generative sampling
An Infinite Hidden Markov Model With Similarity-Biased Transitions
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 |
|---|---|---|---|
| Add similarity-biased local transitions | HDP-HMM-LT · Cocktail Party | F1 score | Helped |
| Add similarity-biased local transitions | HDP-HMM-LT · Bach chorales test set | marginal log likelihood | Helped |
| Add similarity-biased local transitions | HDP-HMM-LT · Bach chorales training set | marginal log likelihood | Hurt |
| Use a Sticky HDP-HMM instead of the vanilla HDP-HMM | HDP-HMM · Cocktail Party | F1 score | Helped |
| Set the similarity decay parameter to a large value when data has no local-transition structure | HDP-HMM-LT · Synthetic data without local transitions | F1 score | Hurt |
| Allow the model to learn the similarity decay parameter | HDP-HMM-LT · Synthetic data without local transitions | F1 score | No clear effect |
| Combine Sticky self-transition bias with local transitions | HDP-HMM-LT · Cocktail Party | F1 score | Helped |
Closest papers by meaning
- RED-HDP-HMM: Observation-Dependent Durations for Bayesian Nonparametric Sequential Models (ICML 2026 · similarity 0.89)
- FlowHMM: Flow-based continuous hidden Markov models (NeurIPS 2022 · similarity 0.86)
- The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains (NeurIPS 2024 · similarity 0.84)
- Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models (ICLR 2025 · similarity 0.84)
- Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context (NeurIPS 2025 · similarity 0.84)
- An Analysis of Tokenization: Transformers under Markov Data (NeurIPS 2024 · similarity 0.84)
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.