A Lagrangian Approach to Fixed Points

NeurIPS 1990 pp. 77-83

/neurips/1990/mjolsness1990neurips-lagrangian/

Abstract

We present a new way to derive dissipative, optimizing dynamics from the Lagrangian formulation of mechanics. It can be used to obtain both standard and novel neural net dynamics for optimization problems. To demonstrate this we derive standard descent dynamics as well as nonstan(cid:173) dard variants that introduce a computational attention mechanism.

PDF NeurIPS Semantic Scholar

Cite

Text

Mjolsness and Miranker. "A Lagrangian Approach to Fixed Points." Neural Information Processing Systems, 1990.

Markdown

[Mjolsness and Miranker. "A Lagrangian Approach to Fixed Points." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/mjolsness1990neurips-lagrangian/)

BibTeX

@inproceedings{mjolsness1990neurips-lagrangian,
  title     = {{A Lagrangian Approach to Fixed Points}},
  author    = {Mjolsness, Eric and Miranker, Willard L.},
  booktitle = {Neural Information Processing Systems},
  year      = {1990},
  pages     = {77-83},
  url       = {https://mlanthology.org/neurips/1990/mjolsness1990neurips-lagrangian/}
}