Our first guest speaker is Emiel Hoogeboom from the University of Amsterdam and you are all cordially invited to the CVG Seminar on March 26th at 1:30 p.m. CET on Zoom (passcode is 809447), where‪ Emiel will give a talk titled “Distributions and Geometry“.

Abstract

Deep generative models aim to model complicated high-dimensional distributions. Among these are Normalizing Flows, a rich family of distributions for many different types of geometry. Normalizing Flows are attractive because in many cases they admit exact likelihood evaluation, and can be designed for fast inference and sampling. Modelling high-dimensional distributions has many applications such as representation learning, outlier detection, variance reduction in estimator, and (conditional) generation. In this talk, we will visit applications of flows on hyperspheres and flows for discrete spaces. Additionally, we talk about graph neural networks with rotational and translational symmetries.

Bio

Emiel is a PhD Student at the University of Amsterdam, working on deep generative modelling under the supervision of Max Welling. Recent works include "Integer Discrete Flows", "Argmax Flows" and "E(n)-equivariant Graph Neural Networks"

Hi everyone! We are thrilled to announce our new monthly CVG Seminars!

Our first guest speaker is Prof. David Ginsbourger from the University of Bern and you are all cordially invited to the CVG Seminar on February 25th at 1:00 p.m. CET on Zoom (passcode is 004934), where‪ David will give a talk titled “Modeling and optimizing set functions via RKHS embeddings“.

Abstract

We consider the issue of modeling and optimizing set functions, with a main focus on kernel methods for expensive objective functions taking finite sets as inputs. Based on recent developments on embeddings of probability distributions in Reproducing Kernel Hilbert Spaces, we explore adaptations of Gaussian Process modeling and Bayesian Optimization to the framework of interest. In particular, combining RKHS embeddings and positive definite kernels on Hilbert spaces delivers a promising class of kernels, as illustrated in particular on two test cases from mechanical engineering and contaminant source localization, respectively. Based on several collaborations and notably on the paper "Kernels over sets of finite sets using RKHS embeddings, with application to Bayesian (combinatorial) optimization" with Poompol Buathong and Tipaluck Krityakierne (AISTATS 2020).

Bio

David Ginsbourger is working at the Institute of Mathematical Statistics and Acturial Sciences of the University of Bern, leading a research group focusing on uncertainty quantification and statistical data science. A significant part of his research deals with Gaussian process modeling and adaptive design of experiments. Further interests encompass kernel design and fitting, and connections between spatial statistics and functional analysis. From the application side, he has been working with a number of colleagues from various disciplines pertaining to engineering and increasingly to geosciences. He completed his PhD in applied mathematics at Ecole Nationale Supérieure des Mines de Saint-Etienne in 2009, and his habilitation in statistics and applied probability at UniBE in 2014. From 2015 to 2020 he was mainly affiliated with Idiap Research institute where he was heading the uncertainty quantification and optimal design group. He received in 2018 a titular professorship from UniBE, where he is now associate (assoziierter) professor.

In this weekly meeting the CVG members come together and discuss recent topics in the Computer Vision and Machine Learning community. In addition there are typically two presentations of selected papers or student projects. 

In this weekly meeting the CVG members come together and discuss recent topics in the Computer Vision and Machine Learning community. In addition there are typically two presentations of selected papers or student projects. 

In this weekly meeting the CVG members come together and discuss recent topics in the Computer Vision and Machine Learning community. In addition there are typically two presentations of selected papers or student projects.