Global optimization on non-convex two-way interaction truncated linear multivariate adaptive regression splines using mixed integer quadratic programming
نویسندگان
چکیده
Multivariate adaptive regression splines (MARS) has been adopted as a popular surrogate function to model the unknown relationships between input and output variables in complex systems. Searching optimal solutions on complicated response surface of MARS serves important tasks various applications. In this paper, we present an efficient effective approach find global value models that incorporate two-way interaction terms which are products truncated linear univariate functions (TITL-MARS). Specifically, with consisting quadratic structures, can reformulate optimization problem TITL-MARS into mixed integer programming (TITL-MARS-OPT), be further solved more principled way. To illustrate effectiveness our proposed TITL-MARS-OPT, come up genetic algorithm gradient descent solve original version TITL-MARS, compared performance benchmark algorithms. Numerical experiments conducted spectrum examples different levels complexity, including 6 existing real world application wind farm optimization. Our successfully efficiently while comparison algorithms fail solution. end, Python code for TITL-MARS-OPT is made available GitHub ( https://github.com/JuXinglong/TITL-MARS-OPT).
منابع مشابه
Unbounded convex sets for non-convex mixed-integer quadratic programming
This paper introduces a fundamental family of unbounded convex sets that arises in the context of non-convex mixed-integer quadratic programming. It is shown that any mixed-integer quadratic program with linear constraints can be reduced to the minimisation of a linear function over a set in the family. Some fundamental properties of the convex sets are derived, along with connections to some o...
متن کاملSemidefinite relaxations for non-convex quadratic mixed-integer programming
We present semidefinite relaxations for unconstrained nonconvex quadratic mixed-integer optimization problems. These relaxations yield tight bounds and are computationally easy to solve for mediumsized instances, even if some of the variables are integer and unbounded. In this case, the problem contains an infinite number of linear constraints; these constraints are separated dynamically. We us...
متن کاملTrajectory Optimization using Mixed-Integer Linear Programming
This thesis presents methods for finding optimal trajectories for vehicles subjected to avoidance and assignment requirements. The former include avoidance of collisions with obstacles or other vehicles and avoidance of thruster plumes from spacecraft. Assignment refers to the inclusion of decisions about terminal constraints in the optimization, such as assignment of waypoints to UAVs and the ...
متن کاملA convex version of multivariate adaptive regression splines
Multivariate adpative regression splines (MARS) provide a flexible statistical modeling method that employs forward and backward search algorithms to identify the combination of basis functions that best fits the data and simultaneously conduct variable selection. In optimization, MARS has been used successfully to estimate the unknown functions in stochastic dynamic programming (SDP), stochast...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information Sciences
سال: 2022
ISSN: ['0020-0255', '1872-6291']
DOI: https://doi.org/10.1016/j.ins.2022.03.041