244 citations · 964 across the 44 of their papers we have counts for
11 papers · 1 filter
Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms
Ambroise Heurtebise, Omar Chehab, Pierre Ablin +2
Causal discovery is a difficult problem that typically relies on strong assumptions on the data-generating model, such as non-Gaussianity. In practice, many modern applications pro…
A noise-corrected Langevin algorithm and sampling by half-denoising
Aapo Hyvärinen
The Langevin algorithm is a classic method for sampling from a given pdf in a real space. In its basic version, it only requires knowledge of the gradient of the log-density, also…
Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning
Aapo Hyvarinen, Ilyes Khemakhem, Hiroshi Morioka
A central problem in unsupervised deep learning is how to find useful representations of high-dimensional data, sometimes called "disentanglement". Most approaches are heuristic an…
Painful intelligence: What AI can tell us about human suffering
Aapo Hyvärinen
This book uses the modern theory of artificial intelligence (AI) to understand human suffering or mental pain. Both humans and sophisticated AI agents process information about the…
Shared Independent Component Analysis for Multi-Subject Neuroimaging
Hugo Richard, Pierre Ablin, Bertrand Thirion +2
We consider shared response modeling, a multi-view learning problem where one wants to identify common components from multiple datasets or views. We introduce Shared Independent C…
Self-supervised representation learning from electroencephalography signals
Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen +3
The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradi…