BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Electronic Structure Reading Group: Clebsch-Gordan Coefficients: M
 aking Sense of Rotations in ML and Beyond
DTSTART:20250723T160000
DTEND:20250723T173000
DTSTAMP:20260406T171932Z
UID:8aa1bfe506c2f63b4f0cedc6bb4d6a9a86ee50bf50f89295e1710461
CATEGORIES:Conferences - Seminars
DESCRIPTION:Michelangelo Domina\nWhen trying to extract the rotational beh
 avior of composite systems\, the result is often a reducible mess - but Cl
 ebsch-Gordan coefficients are the elegant tools we use to restore order. T
 hey tell us how to decompose tensor products into irreducible representati
 ons and how to keep track of what’s actually transforming nicely under r
 otations.\n\nIn the seminar\, we’ll take a practical\, example-driven to
 ur through the world of Clebsch-Gordan coefficients and their role in maki
 ng sense of transformations\, particularly in Machine Learning (ML)\, wher
 e we often target quantities with well-defined rotational behavior.\n\nWe
 ’ll follow a hands-on approach to rotations and their decomposition into
  irreducible components\, all while building intuition for how this machin
 ery really works\, and what it means. With just enough math to keep everyt
 hing honest.\n\nWhile one goal is to understand why this formalism is so w
 idespread in the ML community\, the broader aim is to equip you with tools
  that are just as useful in other fields where angular momentum decomposit
 ion plays a key role - from quantum field theory to spin-½ representation
 s of electrons\, to the Dirac belt trick (sometimes good for parties).\n\n
 My favorite references that use the Clebsch-Gordan contractions in ML:\nDr
 autz\, Atomic cluster expansion for accurate and transferable interatomic 
 potentials\, Phys. Rev. B 100\, 249901 (2019).\nBatatia et al.\, MACE: Hig
 her Order Equivariant Message Passing Neural Networks for Fast and Accurat
 e Force Fields\, NeurIPS (2022).\nNigam et al.\, Recursive evaluation and 
 iterative contraction of N-body equivariant features\, J. Chem. Phys. 153\
 , 121101 (2020).\nBartók et al.\, On representing chemical environments\,
  Phys. Rev. B 87\, (2017).\nBatzner et al.\, E(3)-equivariant graph neural
  networks for data-efficient and accurate interatomic potentials\, Nat. Co
 mmun. 13\, 2453 (2022).\n\nMy favourite reference book for this:\nVarshalo
 vich\, et. al. Quantum Theory of Angular Momentum (1988).\n\nThis event is
  jointly organized with the COSMO seminar.\n---\nThe electronic structure 
 reading group brings together researchers and students interested in mathe
 matical aspects of electronic structure problems and adjacent topics\, inc
 luding:\n\n	Density Functional Theory\n	Many-body Schrödinger equation fo
 r electrons\n	Born-Oppenheimer Molecular Dynamics\n	Numerical analysis and
  error control\n\nFor updates\, join the matrix chat room at #electronic-
 structure:epfl.ch (requires a GASPAR account).\n\nWebsite: https://matma
 t.org/readinggroup/
LOCATION:MA B1 524 https://plan.epfl.ch/?room==MA%20B1%20524
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR