Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Preprints and Working Papers
  4. Chemical machine learning with kernels: The key impact of loss functions
 
working paper

Chemical machine learning with kernels: The key impact of loss functions

Nguyen, Van Quang  
•
De, Sandip  
•
Lin, Junhong  
Show more
2018

Machine learning promises to accelerate materials discovery by allowing computational efficient property predictions from a small number of reference calculations. As a result, the literature spent a considerable effort in designing representations that capture basic physical properties so far. In stark contrast, our work focuses on the less-studied learning formulations in this context in order to exploit inner structures in the prediction errors. In particular, we propose to directly optimize basic loss functions of the prediction error metrics typically used in the literature, such as the mean absolute error or the worst case error. We show that a proper choice of the loss function can directly improve the prediction performance in the desired metric, albeit at the cost of additional computations during training. To support this claim, we describe the statistical learning theoretic foundations and provide numerical evidence with the prediction of atomization energies for a database of small organic molecules

  • Files
  • Details
  • Metrics
Type
working paper
Author(s)
Nguyen, Van Quang  
De, Sandip  
Lin, Junhong  
Cevher, Volkan  orcid-logo
Date Issued

2018

Subjects

Atomization energies prediction

•

Convex optimization

•

Quantum machine learning

•

SOAP-Average kernel

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
LIONS  
COSMO  
Available on Infoscience
February 5, 2018
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/144638
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés