BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Tensor-Reduced Atomic Density Representations - James Darby\, Univ
 ersity of Warwick
DTSTART:20240311T143000Z
DTEND:20240311T150000Z
UID:TALK212938@talks.cam.ac.uk
CONTACT:Eszter Varga-Umbrich
DESCRIPTION:Density-based representations of atomic environments that are 
 invariant under Euclidean symmetries have become a widely used tool in the
  machine learning of interatomic potentials\, broader data-driven atomisti
 c modeling\, and the visualization and analysis of material datasets. The 
 standard mechanism used to incorporate chemical element information is to 
 create separate densities for each element and form tensor products betwee
 n them. This leads to a steep scaling in the size of the representation as
  the number of elements increases. Graph neural networks\, which do not ex
 plicitly use density representations\, escape this scaling by mapping the 
 chemical element information into a fixed dimensional space in a learnable
  way. By exploiting symmetry\, we recast this approach as tensor factoriza
 tion of the standard neighbour-density-based descriptors and\, using a new
  notation\, identify connections to existing compression algorithms. In do
 ing so\, we form compact tensor-reduced representation of the local atomic
  environment whose size does not depend on the number of chemical elements
 \, is systematically convergable\, and therefore remains applicable to a w
 ide range of data analysis and regression tasks.
LOCATION:Zoom link: https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHpt
 UXlRSkppQT09
END:VEVENT
END:VCALENDAR