Discrete-to-continuum graphical methods for large-data clustering, classification and segmentationMS17

Graph methods for machine learning have been found to be extraordinarily successful in several imaging and data analysis applications. They aim to build a graph from the data by encoding similarities between elements and use possible non-local similarity measures for comparison, clustering and classification. The study of large-data limits of state-of-the-art graph models such as Ginzburg-Landau functionals, Cheeger cuts etc. is fundamental for the design of efficient optimisation strategies. In this mini-symposium we gather experts in the field of mathematical graph modelling and large-data convergence to highlight analogies and differences between continuum and discrete variational models for data analysis.

Wed 06 June at 09:30 in Room M (Palazzina B - Building B floor 0)
Scaling Results in Lp Regularised Semi-Supervised Learning
Matthew Thorpe ( University of Cambridge )
Discrete to continuum limit of the graph Ginzburg-Landau functional
Yves van Gennip ( University of Nottingham )
Classification of infinite dimensional data with the Ginzburg-Landau functional
Florian Theil ( University of Warwick )
Large data and zero noise limits of graph-based semi-supervised learning algorithms
Matt Dunlop ( Caltech )
Luca Calatroni ( CMAP, École Polytechnique CNRS )
Daniel Tenbrinck ( University of Münster )
Matthew Thorpe ( University of Cambridge )
bayesian methods, graphical methods, image reconstruction, image segmentation, machine learning, partial differential equation models