SAVE THE DATE! DATAIA Seminar - "Nonlinear independent component analysis" - Aapo Hyvärinen
Aapo Hyvärinen leads DATAIA Seminar
He will illustrate and discuss the nonlinear Independent Component Analysis (ICA), the method that overcomes this problem; his contributions to the topic; and the connection between nonlinear ICA and Variational AutoEncoders (VAE).
"Unsupervised learning, in particular learning general nonlinear representations, is one of the deepest problems in machine learning. Estimating latent quantities in a generative model provides a principled framework, and has been successfully used in the linear case, e.g. with independent component analysis (ICA) and sparse coding. However, extending ICA to the nonlinear case has proven to be extremely difficult: A straight-forward extension is unidentifiable, i.e. it is not possible to recover those latent components that actually generated the data. Here, we show that this problem can be solved by using additional information either in the form of temporal structure or an additional, auxiliary variable. As a first approach, we formulate self-supervised learning schemes which are similar to those heuristically proposed in computer vision. Our main contribution is to provide a rigorous theoretical framework for such self-supervised algorithms, proving that they are able to solve the nonlinear ICA problem. We further show how a connection between nonlinear ICA and variational autoencoders (VAE): While ordinary VAE suffers from the lack of identifiability, conditioning by auxiliary variables leads to identifiability and provides another method for learning nonlinear ICA."
Aapo Hyvarinen studied mathematics at the universities of Helsinki (Finland), Vienna (Austria), and Paris (France), and obtained a Ph.D. degree in Information Science at the Helsinki University of Technology in 1997. From 2016 to 2019, he was Professor at the Gatsby Computational Neuroscience Unit, University College London, UK. Currently he is visiting DATAIA at Inria-Saclay for a year.
Aapo Hyvarinen is the main author of the books « Independent Component Analysis » (2001) and « Natural Image Statistics » (2009), and author or coauthor of more than 200 scientific articles. He is Action Editor at the Journal of Machine Learning Research and Neural Computation and Editorial Board Member in Foundations and Trends in Machine Learning. His current work concentrates on unsupervised machine learning and its applications to neuroscience.
The seminar will take place on 9th October from 2pm to 4pm at Centre Inria-Saclay.
Registration free but mandatory within the limit of available seats
For security reasons, no access to the conference room for unregistered participants