Timezone: »

 
Poster
Flowification: Everything is a normalizing flow
Bálint Máté · Samuel Klein · Tobias Golling · François Fleuret

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #917
in Poster Session 3 »

The two key characteristics of a normalizing flow is that it is invertible (in particular, dimension preserving) and that it monitors the amount by which it changes the likelihood of data points as samples are propagated along the network. Recently, multiple generalizations of normalizing flows have been introduced that relax these two conditions \citep{nielsen2020survae,huang2020augmented}. On the other hand, neural networks only perform a forward pass on the input, there is neither a notion of an inverse of a neural network nor is there one of its likelihood contribution. In this paper we argue that certain neural network architectures can be enriched with a stochastic inverse pass and that their likelihood contribution can be monitored in a way that they fall under the generalized notion of a normalizing flow mentioned above. We term this enrichment \emph{flowification}. We prove that neural networks only containing linear and convolutional layers and invertible activations such as LeakyReLU can be flowified and evaluate them in the generative setting on image datasets.

Keywords: normalizing flows
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Bálint Máté (University of Geneva)
Samuel Klein (University of Geneva, Switzerland)
Tobias Golling (University of Geneva)
François Fleuret (University of Geneva)

François Fleuret got a PhD in Mathematics from INRIA and the University of Paris VI in 2000, and an Habilitation degree in Mathematics from the University of Paris XIII in 2006. He is Full Professor in the department of Computer Science at the University of Geneva, and Adjunct Professor in the School of Engineering of the École Polytechnique Fédérale de Lausanne. He has published more than 80 papers in peer-reviewed international conferences and journals. He is Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence, serves as Area Chair for NeurIPS, AAAI, and ICCV, and in the program committee of many top-tier international conferences in machine learning and computer vision. He was or is expert for multiple funding agencies. He is the inventor of several patents in the field of machine learning, and co-founder of Neural Concept SA, a company specializing in the development and commercialization of deep learning solutions for engineering design. His main research interest is machine learning, with a particular focus on computational aspects and sample efficiency.

More from the Same Authors