A Caltech Library Service

Constrained Differential Optimization

Platt, John C. and Barr, Alan H. (1988) Constrained Differential Optimization. In: Neural Information Processing Systems. American Institute of Physics , New York, NY, pp. 612-621. ISBN 0883185695.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Many optimization models of neural networks need constraints to restrict the space of outputs to a subspace which satisfies external criteria. Optimizations using energy methods yield "forces" which act upon the state of the neural network. The penalty method, in which quadratic energy constraints are added to an existing optimization energy, has become popular recently, but is not guaranteed to satisfy the constraint conditions when there are other forces on the neural model or when there are multiple constraints. In this paper, we present the basic differential multiplier method (BDMM), which satisfies constraints exactly; we create forces which gradually apply the constraints over time, using "neurons" that estimate Lagrange multipliers. The basic differential multiplier method is a differential version of the method of multipliers from Numerical Analysis. We prove that the differential equations locally converge to a constrained minimum. Examples of applications of the differential method of multipliers include enforcing permutation codewords in the analog decoding problem and enforcing valid tours in the traveling salesman problem.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© American Institute of Physics 1988. This paper was supported by an AT&T Bell Laboratories fellowship (JCP).
Funding AgencyGrant Number
AT&T Bell LaboratoriesUNSPECIFIED
Record Number:CaltechAUTHORS:20160107-151945992
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:63457
Deposited By: Kristin Buxton
Deposited On:19 Jan 2016 22:34
Last Modified:03 Oct 2019 09:28

Repository Staff Only: item control page