Timezone: »

Variational Mixture of HyperGenerators for Learning Distributions over Functions
Batuhan Koyuncu · Pablo Sanchez Martin · Ignacio Peis · Pablo Olmos · Isabel Valera

Thu Jul 27 01:30 PM -- 03:00 PM (PDT) @ Exhibit Hall 1 #432

Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces. However, they are computationally costly when dealing with inference tasks, such as missing data imputation, or directly cannot tackle them. In this work, we propose a novel deep generative model, named VaMoH. VaMoH combines the capabilities of modeling continuous functions using INRs and the inference capabilities of Variational Autoencoders (VAEs). In addition, VaMoH relies on a normalizing flow to define the prior, and a mixture of hypernetworks to parametrize the data log-likelihood. This gives VaMoH a high expressive capability and interpretability. Through experiments on a diverse range of data types, such as images, voxels, and climate data, we show that VaMoH can effectively learn rich distributions over continuous functions. Furthermore, it can perform inference-related tasks, such as conditional super-resolution generation and in-painting, as well or better than previous approaches, while being less computationally demanding.

Author Information

Batuhan Koyuncu (Saarland University)
Pablo Sanchez Martin (Max Planck Institute for Intelligent Systems)
Ignacio Peis (Universidad Carlos III de Madrid)
Ignacio Peis

I am interested in the connection between Deep Learning and Probabilistic Modelling. My current research lies in creating more expressive generative models of data and functions. My aims are increasing their robustness (e.g. dealing with mixed-type data incomplete data), developing better inference methods, or using hypernetworks to handle functions. My work has been applied to several fields, like Neuroscience or Psychiatry.

Pablo Olmos (Univdrsity Carlos III Madrid)
Isabel Valera (Saarland University)

Isabel Valera is a full Professor on Machine Learning at the Department of Computer Science of Saarland University in Saarbrücken (Germany), and Adjunct Faculty at MPI for Software Systems in Saarbrücken (Germany). She is also a scholar of the European Laboratory for Learning and Intelligent Systems (ELLIS). Prior to this, she was an independent group leader at the MPI for Intelligent Systems in Tübingen (Germany). She has held a German Humboldt Post-Doctoral Fellowship, and a “Minerva fast track” fellowship from the Max Planck Society. She obtained her PhD in 2014 and MSc degree in 2012 from the University Carlos III in Madrid (Spain), and worked as postdoctoral researcher at the MPI for Software Systems (Germany) and at the University of Cambridge (UK). Her research focuses on developing machine learning methods that are flexible, robust, interpretable and fair to analyze real-world data.

More from the Same Authors