DeepAI AI Chat
Log In Sign Up

Fighting the curse of dimensionality: A machine learning approach to finding global optima

by   Julian F. Schumann, et al.

Finding global optima in high-dimensional optimization problems is extremely challenging since the number of function evaluations required to sufficiently explore the design space increases exponentially with its dimensionality. Furthermore, non-convex cost functions render local gradient-based search techniques ineffective. To overcome these difficulties, here we demonstrate the use of machine learning to find global minima, whereby autoencoders are used to drastically reduce the search space dimensionality, and optima are found by surveying the lower-dimensional latent spaces. The methodology is tested on benchmark functions and on a structural optimization problem, where we show that by exploiting the behavior of certain cost functions we either obtain the global optimum at best or obtain superior results at worst when compared to established optimization procedures.


page 9

page 14

page 41


Why Do Local Methods Solve Nonconvex Problems?

Non-convex optimization is ubiquitous in modern machine learning. Resear...

Finding Global Minima via Kernel Approximations

We consider the global minimization of smooth functions based solely on ...

Multiscale semidefinite programming approach to positioning problems with pairwise structure

We consider the optimization of pairwise objective functions, i.e., obje...

An approximate Itô-SDE based simulated annealing algorithm for multivariate design optimization problems

This research concerns design optimization problems involving numerous d...

Search for Common Minima in Joint Optimization of Multiple Cost Functions

We present a novel optimization method, named the Combined Optimization ...

Neural Generative Models for Global Optimization with Gradients

The aim of global optimization is to find the global optimum of arbitrar...

Global Optimum Search in Quantum Deep Learning

This paper aims to solve machine learning optimization problem by using ...