Research map / Label-efficient and robust learning / Recognition and long-tail
Completing State Representations using Spectral Learning
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 |
|---|---|---|---|
| augment spectral PSR learning with a domain-knowledge feature function f (PSR-f) | standard spectral PSR · synthetic HMMs (ring and random topology), sample size 1000 | relative log-loss | Helped |
| use f alone as the state instead of PSR-f (ablation) | PSR-f · synthetic HMMs | relative log-loss | Hurt |
| add 3 irrelevant features to f (dummy-3 vs dummy-0) (ablation) | PSR-f · synthetic HMMs | relative log-loss | Mixed |
| PSR-f versus PSR and f-only | PSR-f · Aircraft Identification, small sample sizes | relative log-loss | Helped |
| increase training sample size in Aircraft Identification | PSR-f versus PSR · Aircraft Identification | relative log-loss | No clear effect |
| PSR-f with 2nd order Markov feature versus PSR and Markov baseline | PSR-f · gene splice dataset | relative log-likelihood and classification accuracy | Helped |
| replace empirical P_{T,H} with exact statistics in standard spectral learning (ablation) | standard spectral learning · RING HMMs, sample size 5000, full rank | relative log-loss | Hurt |
Closest papers by meaning
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.87)
- Identifying latent state transitions in non-linear dynamical systems (ICLR 2025 · similarity 0.87)
- SpectraLDS: Provable Distillation for Linear Dynamical Systems (NeurIPS 2025 · similarity 0.86)
- Spectral Alignment in Forward–Backward Representations via Temporal Abstraction (NeurIPS 2026 · similarity 0.85)
- Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data (ICLR 2025 · similarity 0.85)
- ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals (ICML 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.