Research map / Time series / Causal and generative time series
Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
Hermanni Hälvä, Sylvain Le Corff, Luc Lehéricy, Jonathan So, Yongjie Zhu, Elisabeth Gassiat, Aapo Hyvarinen
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 |
|---|---|---|---|
| use Delta-SNICA instead of IIA-HMM, LGSSM and iVAE* for recovering latent components | Delta-SNICA · simulated data, MLP mixing with 1/2/3/5 layers | mean absolute correlation coefficient (MCC) | Improved |
| use Delta-SNICA instead of baselines for denoising | Delta-SNICA · simulated data, noise-free observation recovery | correlation with ground-truth noise-free data | No clear effect |
| use Delta-SNICA features instead of IIA-HMM and IIA-TCL | Delta-SNICA · Cam-CAN MEG stimulus classification | classification accuracy | Improved |
Closest papers by meaning
- Beyond ICA: Identifiability by Symmetry Breaking (NeurIPS 2026 · similarity 0.87)
- Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability (NeurIPS 2025 · similarity 0.87)
- Robustness of Nonlinear Representation Learning (ICML 2024 · similarity 0.87)
- Multi-View Causal Representation Learning with Partial Observability (ICLR 2024 · similarity 0.85)
- On the Identifiability of Switching Dynamical Systems (ICML 2024 · similarity 0.85)
- When does LeJEPA learn a World Model? (NeurIPS 2026 · 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.
