Data fitting with geometric-programming-compatible softmax functions
Name
11081_2016_9332_ReferencePDF.pdf
Size
427.73 KB
Format
Adobe PDF
Checksum (MD5)
7b941506a360c239f2fbe9aba4f53e30
Author(s)
Abbeel, Pieter
Hoburg, Warren W
Kirschen, Philippe Gilbert
Date Issued
August 2016
Journal
Optimization and Engineering
Publisher
Springer US
Citation
Hoburg, Warren, Philippe Kirschen, and Pieter Abbeel. “Data Fitting with Geometric-Programming-Compatible Softmax Functions.” Optimization and Engineering 17.4 (2016): 897–918.
Version
Author's final manuscript
Abstract
Motivated by practical applications in engineering, this article considers the problem of approximating a set of data with a function that is compatible with geometric programming (GP). Starting with well-established methods for fitting max-affine functions, it is shown that improved fits can be obtained using an extended function class based on the softmax of a set of affine functions. The softmax is generalized in two steps, with the most expressive function class using an implicit representation that allows fitting algorithms to locally tune softness. Each of the proposed function classes is directly compatible with the posynomial constraint forms in GP. Max-monomial fitting and posynomial fitting are shown to correspond to fitting special cases of the proposed implicit softmax function class. The fitting problem is formulated as a nonlinear least squares regression, solved locally using a Levenberg–Marquardt algorithm. Practical implementation considerations are discussed. The article concludes with numerical examples from aerospace engineering and electrical engineering.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s11081-016-9332-3
