---
res:
  bibo_abstract:
  - The depth of networks plays a crucial role in the effectiveness of deep learning.
    However, the memory requirement for backpropagation scales linearly with the number
    of layers, which leads to memory bottlenecks during training. Moreover, deep networks
    are often unable to handle time-series data appearing at irregular intervals.
    These issues can be resolved by considering continuous-depth networks based on
    the neural ODE framework in combination with reversible integration methods that
    allow for variable time-steps. Reversibility of the method ensures that the memory
    requirement for training is independent of network depth, while variable time-steps
    are required for assimilating time-series data on irregular intervals. However,
    at present, there are no known higher-order reversible methods with this property.
    High-order methods are especially important when a high level of accuracy in learning
    is required or when small time-steps are necessary due to large errors in time
    integration of neural ODEs, for instance in context of complex dynamical systems
    such as Kepler systems and molecular dynamics. The requirement of small time-steps
    when using a low-order method can significantly increase the computational cost
    of training as well as inference. In this work, we present an approach for constructing
    high-order reversible methods that allow adaptive time-stepping. Our numerical
    tests show the advantages in computational speed when applied to the task of learning
    dynamical systems.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Sofya
      foaf_name: Maslovskaya, Sofya
      foaf_surname: Maslovskaya
      foaf_workInfoHomepage: http://www.librecat.org/personId=87909
  - foaf_Person:
      foaf_givenName: Sina
      foaf_name: Ober-Blöbaum, Sina
      foaf_surname: Ober-Blöbaum
      foaf_workInfoHomepage: http://www.librecat.org/personId=16494
  - foaf_Person:
      foaf_givenName: Christian
      foaf_name: Offen, Christian
      foaf_surname: Offen
      foaf_workInfoHomepage: http://www.librecat.org/personId=85279
    orcid: 0000-0002-5940-8057
  - foaf_Person:
      foaf_givenName: Pranav
      foaf_name: Singh, Pranav
      foaf_surname: Singh
  - foaf_Person:
      foaf_givenName: Boris Edgar
      foaf_name: Wembe Moafo, Boris Edgar
      foaf_surname: Wembe Moafo
      foaf_workInfoHomepage: http://www.librecat.org/personId=95394
  dct_date: 2025^xs_gYear
  dct_language: eng
  dct_title: Adaptive higher order reversible integrators for memory efficient deep
    learning@
...