BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Maximilian Nickel (Facebook AI)
DTSTART:20220711T073000Z
DTEND:20220711T083000Z
DTSTAMP:20260422T214712Z
UID:GaML/1
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/1/">Rep
 resentation Learning and Generative Modeling on Manifolds</a>\nby Maximili
 an Nickel (Facebook AI) as part of Workshop on Geometry and Machine Learni
 ng\n\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/GaML/1/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Nicolas Guigui (CNRS)
DTSTART:20220711T090000Z
DTEND:20220711T103000Z
DTSTAMP:20260422T214712Z
UID:GaML/2
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/2/">Int
 roduction to Geometric Statistics with Geomstats I</a>\nby Nicolas Guigui 
 (CNRS) as part of Workshop on Geometry and Machine Learning\n\nAbstract: T
 BA\n
LOCATION:https://researchseminars.org/talk/GaML/2/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Beatrice Pozzetti (Heidelberg)
DTSTART:20220711T120000Z
DTEND:20220711T124000Z
DTSTAMP:20260422T214712Z
UID:GaML/3
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/3/">Gra
 ph Embeddings in Symmetric Spaces</a>\nby Beatrice Pozzetti (Heidelberg) a
 s part of Workshop on Geometry and Machine Learning\n\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/GaML/3/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Pim de Haan (Amsterdam)
DTSTART:20220711T130000Z
DTEND:20220711T134000Z
DTSTAMP:20260422T214712Z
UID:GaML/4
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/4/">Gau
 ge Equivariant Mesh Convolutional Neural Networks</a>\nby Pim de Haan (Ams
 terdam) as part of Workshop on Geometry and Machine Learning\n\n\nAbstract
 \nConvolutional neural networks are widely successful in deep learning on 
 image datasets. However\, some data\, like that resulting from MRI scans\,
  do not reside on a square grid\, but instead live on curved manifolds\, d
 iscretized as meshes. A key issue on such meshes is that they lack a local
  notion of direction and hence the convolutional kernel cannot be canonica
 lly oriented. By doing message passing on the mesh and defining a groupoid
  of similar messages that should share weights\, we propose a gauge equiva
 riant method of building a CNN on such meshes that is direction-aware\, ye
 t agnostic to how the directions are chosen. It is scalable\, invariant to
  how the mesh is rotated\, and performs state-of-the-art on a medical appl
 ication for estimating blood flow through human arteries.\n
LOCATION:https://researchseminars.org/talk/GaML/4/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Xavier Pennec (INRIA)
DTSTART:20220712T073000Z
DTEND:20220712T083000Z
DTSTAMP:20260422T214712Z
UID:GaML/5
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/5/">Geo
 metric Statistics for Computational Anatomy</a>\nby Xavier Pennec (INRIA) 
 as part of Workshop on Geometry and Machine Learning\n\n\nAbstract\nAt the
  interface of geometry\, statistics\, image analysis and medicine\, comput
 ational anatomy aims at analysing and modelling the biological variability
  of the organs shapes and their dynamics at the population level. The goal
  is to model the mean anatomy\, its normal variation\, its motion / evolut
 ion and to discover morphological differences between normal and pathologi
 cal groups. However\, shapes are usually described by equivalence classes 
 of sets of points\, curves\, surfaces or images under the action of a tran
 sformation group\, or directly by the diffeomorphic deformation of a templ
 ate in diffeomorphometry. This implies that they live in non-linear spaces
 \, while statistics where essentially developed in a Euclidean framework. 
 For instance\, adding or subtracting curves or surfaces does not really ma
 ke sense. Thus\, there is a need for redefining a consistent statistical f
 ramework for objects living in manifolds and Lie groups\, a field which is
  now called geometric statistics. The objective of this talk is to give an
  overview of the Riemannian computational tools and of simple statistics i
 n these spaces. The talk is motivated and illustrated by applications in m
 edical image analysis\, such as the regression of simple and efficient mod
 els of the atrophy of the brain in Alzheimer’s disease and the groupwise
  analysis of the motion of the heart in sequences of images using the para
 llel transport of surface and image deformations.\n
LOCATION:https://researchseminars.org/talk/GaML/5/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Maxim Kochurov (PyMC Labs)
DTSTART:20220712T090000Z
DTEND:20220712T103000Z
DTSTAMP:20260422T214712Z
UID:GaML/6
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/6/">Hyp
 erbolic Manifolds in Deep Learning I</a>\nby Maxim Kochurov (PyMC Labs) as
  part of Workshop on Geometry and Machine Learning\n\n\nAbstract\nHyperbol
 ic manifolds are quite new in deep learning. Mathematical elegance and the
 oretical advantages are very attractive properties for dimensionality redu
 ction and rich representations. Moreover\, a lot of research was done to i
 nvestigate opportunities in graph-based deep learning or language models. 
 In the talk I’ll give an overview of what are the main advances in the a
 rea\, highlighting the most problematic theory and motivation. During the 
 practical session\, we’ll get familiar with models and implementations t
 hat make use of the hyperbolic space to their fullest potential.\n
LOCATION:https://researchseminars.org/talk/GaML/6/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Björn Ommer (LMU Munich)
DTSTART:20220712T120000Z
DTEND:20220712T124000Z
DTSTAMP:20260422T214712Z
UID:GaML/7
DESCRIPTION:by Björn Ommer (LMU Munich) as part of Workshop on Geometry a
 nd Machine Learning\n\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/GaML/7/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Erik Bekkers (Amsterdam)
DTSTART:20220712T130000Z
DTEND:20220712T134000Z
DTSTAMP:20260422T214712Z
UID:GaML/8
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/8/">Geo
 metric and Physical Quantities improve E(3) Equivariant Message Passing</a
 >\nby Erik Bekkers (Amsterdam) as part of Workshop on Geometry and Machine
  Learning\n\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/GaML/8/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Emanuele Rodolà (Sapienza University)
DTSTART:20220713T073000Z
DTEND:20220713T083000Z
DTSTAMP:20260422T214712Z
UID:GaML/9
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/9/">Fro
 m Sound to Metric Priors: A New Paradigm for Shape Generation</a>\nby Eman
 uele Rodolà (Sapienza University) as part of Workshop on Geometry and Mac
 hine Learning\n\n\nAbstract\nSpectral and metric geometry are at the heart
  of various problems in computer vision\, graphics\, pattern recognition\,
  and machine learning. Ultimately\, the core reason for their success can 
 be traced down to questions of stability and to the informativeness of the
  eigenvalues of certain operators. In this talk\, I will discuss and show 
 tangible examples of such properties and showcase some dramatic implicatio
 ns on a selection of notoriously hard problems in computer vision and grap
 hics. First\, I will address the question of whether one can recover the s
 hape of a geometric object from its vibration frequencies (‘hear the sha
 pe of the drum’)\; while theoretically the answer to this question is ne
 gative\, little is known about the practical possibility of using the spec
 trum for shape reconstruction and optimization. I will introduce a numeric
 al procedure called isospectralization\, as well as a data-driven variant\
 , showing how this *practical* problem is solvable. Then\, I will discuss 
 the increasingly popular task of designing an effective generative model f
 or deformable 3D shapes. I will demonstrate how injecting metric distortio
 n priors into a simple geometric reconstruction loss can lead to the forma
 tion of a very informative latent space\, which can be trained with extrem
 ely scarce data (less than 10 examples) and still yield competitive genera
 tion quality as well as aiding geometric disentanglement.\n
LOCATION:https://researchseminars.org/talk/GaML/9/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Anastasis Kratsios (McMaster)
DTSTART:20220713T090000Z
DTEND:20220713T094000Z
DTSTAMP:20260422T214712Z
UID:GaML/10
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/10/">Em
 bedding Guarantees for Representations by Small Probabilistic Graph Transf
 ormers</a>\nby Anastasis Kratsios (McMaster) as part of Workshop on Geomet
 ry and Machine Learning\n\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/GaML/10/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Nicolas Guigui (CNRS)
DTSTART:20220713T110000Z
DTEND:20220713T123000Z
DTSTAMP:20260422T214712Z
UID:GaML/11
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/11/">In
 troduction to Geometric Statistics with Geomstats II</a>\nby Nicolas Guigu
 i (CNRS) as part of Workshop on Geometry and Machine Learning\n\nAbstract:
  TBA\n
LOCATION:https://researchseminars.org/talk/GaML/11/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Maxim Kochurov (PyMC Labs)
DTSTART:20220713T130000Z
DTEND:20220713T143000Z
DTSTAMP:20260422T214712Z
UID:GaML/12
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/GaML/12/">Hy
 perbolic Manifolds in Deep Learning II</a>\nby Maxim Kochurov (PyMC Labs) 
 as part of Workshop on Geometry and Machine Learning\n\n\nAbstract\nHyperb
 olic manifolds are quite new in deep learning. Mathematical elegance and t
 heoretical advantages are very attractive properties for dimensionality re
 duction and rich representations. Moreover\, a lot of research was done to
  investigate opportunities in graph-based deep learning or language models
 . In the talk I’ll give an overview of what are the main advances in the
  area\, highlighting the most problematic theory and motivation. During th
 e practical session\, we’ll get familiar with models and implementations
  that make use of the hyperbolic space to their fullest potential.\n
LOCATION:https://researchseminars.org/talk/GaML/12/
END:VEVENT
END:VCALENDAR