Beyond independent component analysis: identifiability and algorithms
- Date
- Jan 29, 2026
- Time
- 3:00 PM - 4:00 PM
- Speaker
- Alvaro Ribot
- Affiliation
- Harvard University
- Language
- en
- Main Topic
- Biologie
- Host
- Local Organisors: Nikola Sadovek, Maximilian Wiesmann, Giulio Zucal
- Description
- Independent Component Analysis (ICA) is a classical method for recovering latent variables with useful identifiability properties. However, full independence is a strong assumption that may not hold in many real-world settings. In this talk, I will discuss how much we can relax the independence assumption without losing identifiability of the model. We show that the weakest such assumption is pairwise mean independence. Our identifiability result is based on a generalization of the spectral theorem from matrices to higher-order tensors, which implies a unique tensor decomposition of the cumulant tensors arising in the model. This is joint work with Anna Seigal and Piotr Zwiernik.
Last modified: Jan 29, 2026, 7:39:49 AM
Location
Max Planck Institute of Molecular Cell Biology and Genetics (MPI-CBG CSBD SR Top Floor (VC))Pfotenhauerstraße10801307Dresden
- Phone
- +49 351 210-0
- Fax
- +49 351 210-2000
- MPI-CBG
- Homepage
- http://www.mpi-cbg.de
Organizer
Max Planck Institute of Molecular Cell Biology and GeneticsPfotenhauerstraße10801307Dresden
- Phone
- +49 351 210-0
- Fax
- +49 351 210-2000
- MPI-CBG
- Homepage
- http://www.mpi-cbg.de
Scan this code with your smartphone and get directly this event in your calendar. Increase the image size by clicking on the QR-Code if you have problems to scan it.
Legend
- Biology
- Chemistry
- Civil Eng., Architecture
- Computer Science
- Economics
- Electrical and Computer Eng.
- Environmental Sciences
- for Pupils
- Law
- Linguistics, Literature and Culture
- Materials
- Mathematics
- Mechanical Engineering
- Medicine
- Physics
- Psychology
- Society, Philosophy, Education
- Spin-off/Transfer
- Traffic
- Training
- Welcome