BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Density Functional Theory and Artificial Intelligence learning fro
 m each other
DTSTART;VALUE=DATE:20250303
DTSTAMP:20260414T104627Z
UID:6d25471a3a236817a8f5549b5c02c41fb06f08845b600a1908e2992c
CATEGORIES:Conferences - Seminars
DESCRIPTION:You can apply to participate and find all the relevant informa
 tion (speakers\, abstracts\, program\,...) on the event website: https://
 www.cecam.org/workshop-details/density-functional-theory-and-artificial-in
 telligence-learning-from-each-other-1281.\n\nRegistration is required to a
 ttend the full event\, take part in the social activities and present a po
 ster at the poster session (if any).  However\, the EPFL community is w
 elcome to attend specific lectures without registration if the topic is
  of interest to their research. Do not hesitate to contact the CECAM Even
 t Manager if you have any question.\n\nDescription\nThe rapid progress of
  Artificial Intelligence (AI) is transforming nearly every facet of scient
 ific research\, with Quantum chemistry and electronic structure theory not
  being exceptions. Density Functional Theory (DFT) [1–5]\, the workhorse
  of these disciplines\, is also undergoing substantial evolution under the
  influence of AI\, leading to significant impacts on molecular and materia
 l simulations at various scales [6–13].\nSpecifically\, AI’s involveme
 nt in DFT serves two main purposes: Firstly\, it is used to improve [1–
 9] and accelerate [2\,10–13] DFT approximations\, thereby striving to r
 esolve or at least alleviate [14] the problems associated with functional
 s designed by humans. Secondly\, AI is being employed to create surrogate 
 models that reproduce DFT results  [15–22\,22–24].  In between these
  two strategies\, there are also “Δ-machine learning” approaches\, wh
 ere (machine learning) ML is used to refine properties derived from DFT an
 d bring them close to wavefunction accuracy [25–27]. Such models facilit
 ate simulations on larger lengths and time scales [18\,22]. The fusion of
  DFT and AI is also revolutionizing chemical research by accelerating high
 -throughput screenings by several orders of magnitude [20\,28\,29].\nIn t
 his workshop\, we will concentrate on the latest advancements at the inter
 section of AI and DFT\, with a specific emphasis on two main areas: AI-pow
 ered improvements of DFT and the development of AI surrogate models aimed 
 at reproducing DFT results. Our goal is to foster knowledge exchange betwe
 en experts working on these interrelated areas and attempt to answer and b
 etter understand the implications of the following open challenges in the 
 two fields:\n \n1.         When and how will AI-learned functiona
 ls attain the broad applicability that their human-designed counterparts a
 lready have?\n2.         Can the strong correlation problem in DFT
  [30–34] be mitigated or even solved by AI?\n3.         How is 
 the lack of variety and reliability of benchmark data for extended systems
 \, and for transition metal molecules [35–37]\, hampering the evolution
  of AI-based DFT methods? What solutions can be applied to rectify this?\n
 4.         Can AI enable further progress in handling dispersion i
 nteractions\, beyond the standard heuristic corrections such as those intr
 oduced by Grimme [38\,39]?\n5.         What strategies can be used t
 o further advance ML-based DFT approximations beyond their current state-o
 f-the-art? For example\, what is next after DM21 [8]? \n6.         C
 an the use of novel DFT features advance ML-DFT [32\,33]?\n7.      
    What are the key challenges in creating Machine Learning models for r
 eal-world applications (e.g.\, catalysts discoveries) that are based on th
 e DFT data [28\,40\,41]? For this question\, we aim to aim to distinguish
  and address the challenges that arise from DFT itself\, and those that ar
 e related to the ML models. Moreover\, we aim to distinguish and address t
 he challenges that arise from DFT itself\, and those that are related to t
 he ML models.\n8.  In what way can ML models be informed by the "zoo" of
  DFT functionals rather than inheriting the bias of a single one?\n \nRef
 erences\n\n[1] S. Vuckovic\, A. Gerolin\, T. Daas\, H. Bahmann\, G. Friese
 cke\, P. Gori‐Giorgi\, WIREs. Comput. Mol. Sci.\, 13\, (2022)\n[2] M. T
 subaki\, T. Mizoguchi\, J. Phys. Chem. Lett.\, 9\, 5733-5741 (2018)\n[3] 
 B. Huang\, G. F. von Rudorff\, and O. A. von Lilienfeld\, Towards Self-Dri
 ving Laboratories: The Central Role of Density Functional Theory in the AI
  Age\, arXiv:2304.03272.\n[4] S. Maier\, E. Collins\, K. Raghavachari\, J.
  Phys. Chem. A\, 127\, 3472-3483 (2023)\n[5] A. Nandi\, C. Qu\, P. Housto
 n\, R. Conte\, J. Bowman\, J. Chem. Phys.\, 154\, 051102 (2021)\n[6] P. U
 nzueta\, C. Greenwell\, G. Beran\, J. Chem. Theory Comput.\, 17\, 826-840
  (2021)\n[7] H. Kulik\, WIREs. Comput. Mol. Sci.\, 10\, (2019)\n[8] J. Ja
 net\, S. Ramesh\, C. Duan\, H. Kulik\, ACS Cent. Sci.\, 6\, 513-524 (2020
 )\n[9] K. Burke\, J. Chem. Phys.\, 136\, 150901 (2012)\n[10] A. Cohen\, P
 . Mori-Sánchez\, W. Yang\, Chem. Rev.\, 112\, 289-320 (2011)\n[11] S. Ch
 miela\, H. Sauceda\, K. Müller\, A. Tkatchenko\, Nat. Commun.\, 9\, 3887
  (2018)\n[12] S. Vuckovic\, P. Gori-Giorgi\, J. Phys. Chem. Lett.\, 8\, 2
 799-2805 (2017)\n[13] F. Liu\, C. Duan\, H. Kulik\, J. Phys. Chem. Lett.\,
  11\, 8067-8076 (2020)\n[14] L. Maurer\, M. Bursch\, S. Grimme\, A. Hanse
 n\, J. Chem. Theory Comput.\, 17\, 6134-6151 (2021)\n[15] B. Chan\, P. Gi
 ll\, M. Kimura\, J. Chem. Theory Comput.\, 15\, 3610-3622 (2019)\n[16] L.
  Goerigk\, A. Hansen\, C. Bauer\, S. Ehrlich\, A. Najibi\, S. Grimme\, Phy
 s. Chem. Chem. Phys.\, 19\, 32184-32215 (2017)\n[17] S. Grimme\, J. Anton
 y\, S. Ehrlich\, H. Krieg\, The Journal of Chemical Physics\, 132\, 15410
 4 (2010)\n[18] E. Caldeweyher\, C. Bannwarth\, S. Grimme\, The Journal of 
 Chemical Physics\, 147\, 034112 (2017)\n[19] M. Wodrich\, R. Laplaza\, N.
  Cramer\, M. Reiher\, C. Corminboeuf\, Chimia.\, 77\, 139 (2023)\n[20] C.
  Duan\, F. Liu\, A. Nandy\, H. Kulik\, J. Phys. Chem. Lett.\, 12\, 4628-4
 637 (2021)\n[21] F. Imoto\, M. Imada\, A. Oshiyama\, Phys. Rev. Research\,
  3\, 033198 (2021)\n[22] F. Brockherde\, L. Vogt\, L. Li\, M. Tuckerman\,
  K. Burke\, K. Müller\, Nat. Commun.\, 8\, 872 (2017)\n[23] R. Nagai\, R
 . Akashi\, O. Sugino\, npj. Comput. Mater.\, 6\, 43 (2020)\n[24] R. Nagai
 \, R. Akashi\, O. Sugino\, Phys. Rev. Research\, 4\, 013106 (2022)\n[25] 
 L. Li\, S. Hoyer\, R. Pederson\, R. Sun\, E. Cubuk\, P. Riley\, K. Burke\,
  Phys. Rev. Lett.\, 126\, 036401 (2021)\n[26] M. Kasim\, S. Vinko\, Phys.
  Rev. Lett.\, 127\, 126403 (2021)\n[27] S. Dick\, M. Fernandez-Serra\, Ph
 ys. Rev. B\, 104\, L161109 (2021)\n[28] J. Kirkpatrick\, B. McMorrow\, D.
  Turban\, A. Gaunt\, J. Spencer\, A. Matthews\, A. Obika\, L. Thiry\, M. F
 ortunato\, D. Pfau\, L. Castellanos\, S. Petersen\, A. Nelson\, P. Kohli\,
  P. Mori-Sánchez\, D. Hassabis\, A. Cohen\, Science\, 374\, 1385-1389 (2
 021)\n[29] H. Ma\, A. Narayanaswamy\, P. Riley\, L. Li\, Sci. Adv.\, 8\, 
 (2022)\n[30] J. Snyder\, M. Rupp\, K. Hansen\, L. Blooston\, K. Müller\, 
 K. Burke\, The Journal of Chemical Physics\, 139\, (2013)\n[31] B. Kalita
 \, L. Li\, R. McCarty\, K. Burke\, Acc. Chem. Res.\, 54\, 818-826 (2021)\
 n[32] R. Meyer\, M. Weichselbaum\, A. Hauser\, J. Chem. Theory Comput.\, 
 16\, 5685-5694 (2020)\n[33] O. Schütt\, J. VandeVondele\, J. Chem. Theory
  Comput.\, 14\, 4168-4175 (2018)\n[34] C. Duan\, A. Nandy\, R. Meyer\, N.
  Arunachalam\, H. Kulik\, Nat. Comput. Sci.\, 3\, 38-47 (2022)\n[35] H. K
 ulik\, Israel Journal of Chemistry\, 62\, (2021)\n[36] O. von Lilienfeld\
 , K. Burke\, Nat. Commun.\, 11\, 4895 (2020)\n[37] L. Fiedler\, K. Shah\,
  M. Bussmann\, A. Cangi\, Phys. Rev. Materials\, 6\, 040301 (2022)\n[38] 
 H. Kulik\, T. Hammerschmidt\, J. Schmidt\, S. Botti\, M. Marques\, M. Bole
 y\, M. Scheffler\, M. Todorović\, P. Rinke\, C. Oses\, A. Smolyanyuk\, S.
  Curtarolo\, A. Tkatchenko\, A. Bartók\, S. Manzhos\, M. Ihara\, T. Carri
 ngton\, J. Behler\, O. Isayev\, M. Veit\, A. Grisafi\, J. Nigam\, M. Cerio
 tti\, K. Schütt\, J. Westermayr\, M. Gastegger\, R. Maurer\, B. Kalita\, 
 K. Burke\, R. Nagai\, R. Akashi\, O. Sugino\, J. Hermann\, F. Noé\, S. Pi
 lati\, C. Draxl\, M. Kuban\, S. Rigamonti\, M. Scheidgen\, M. Esters\, D. 
 Hicks\, C. Toher\, P. Balachandran\, I. Tamblyn\, S. Whitelam\, C. Belling
 er\, L. Ghiringhelli\, Electron. Struct.\, 4\, 023004 (2022)\n[39] A. Nan
 dy\, C. Duan\, M. Taylor\, F. Liu\, A. Steeves\, H. Kulik\, Chem. Rev.\, 
 121\, 9927-10000 (2021)\n[40] M. Bogojeski\, L. Vogt-Maranto\, M. Tuckerma
 n\, K. Müller\, K. Burke\, Nat. Commun.\, 11\, 5223 (2020)
LOCATION:BCH 2103 https://plan.epfl.ch/?room==BCH%202103
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR