Seminars in 2022
Trace-class Gaussian priors for Bayesian learning of neural networks with MCMC
Torben Sell, University of Edinburgh, Scotland online, please contact us beforehand if you would like to join10:15 - 11:30
I will discuss a new neural network based prior for real valued functions on ℝ^d. The new prior is a Gaussian neural network prior, where each weight…
more ›On the duality for nonlinear filtering
Jin W. Kim, University of Illinois at Urbana-Champaign, USA Campus Golm, Building 9, Room 2.2210:00 - 11:30
In this talk, I will present the dual control system for the hidden Markov model (HMM). This is a direct extension of classical duality between…
more ›"Stochastic gradient descent in continuous time: discrete and continuous data" and "Augmenting Bayesian inference with possibility theory"
Jonas Latz (Heriot-Watt University, Edinburgh) & Jeremie Houssineau (University of Warwick, UK) Campus Golm, Building 5, Room 1.1010:00-12:00
Jonas Latz:
Optimisation problems with discrete and continuous data appear in statistical estimation, machine learning, functional data science,…
more ›Stochastic Modelling with few Parameters
Philipp Meyer, UFS Data-centric Sciences, University of Potsdam Campus Golm, Building 9, Room 0.1210:15-11:15
Simple stochastic models can describe the fluctuations of a time series. A good way to get a first impression of the data is to look at the mean…
more ›Toward a unified framework for large scale imaging problems: Theory, applications, and potential issues
Hossein S. Aghamiry, Université Côte d'Azur, Geoazur, Valbonne, France Campus Golm, Building 9, Room 1.1012:15-13:15
Visualizing and quantifying the properties of a medium using sparse indirect measurements is the final goal of all the imaging methods in different…
more ›Learning in High-Dimensional Feature Spaces Using ANOVA-Based Fast Matrix-Vector Multiplication
Theresa Wagner, TU Chemnitz Campus Golm, building 9, room 0.1716:00-17:00
Kernel matrices are crucial in many learning tasks and typically dense and large-scale. Depending on the dimension of the feature space even the…
more ›IRTG Workshop - Good Scientific Practice
Dr. Peter Schröder Campus Golm, building 29, room 0.25/0.2610:00-17:00
This workshop is part of the SFB IRTG Certificate Program and will be held by Dr. Peter Schröder. The onsite workshop wil deal with Good Scientif…
more ›"Two prior models for edge-preserving Bayesian inversion" & "Geometry Parameter Estimation for Sparse X-ray Log Imaging"
Felipe Uribe & Angelina Senchukova, LUT University, Finland Campus Golm, building 9, room 1.2210:15 - 11:15
Abstract by Felipe Uribe:
In inverse problems arising in imaging science characterization of sharp edges in the solution is desired. Within the…
more ›'Projected Particle Filtering' and 'On ensemble size in a particle method for subsidence estimation'
Svetlana Dubinkina (VU Amsterdam) and Femke C. Vossepoel (TU Delft) Campus Golm, building 9, room 1.2210:00 - 11:00
Abstract by Svetlana Dubinkina:
Data assimilation of high-dimensional nonlinear models is subject to curse of dimensionality. It is when an ensemble…
more ›Bayesian and Deterministic Spatio-Temporal Methods with Edge-Preserving Priors for Inverse Problems
Mirjeta Pasha, Tufts University, US Campus Golm, building 9, room 1.1012:13 - 13:15
Inverse problems are ubiquitous in many fields of science such as engineering, biology, medical imaging, atmospheric science, and geophysics. Three…
more ›