Scalability of using Restricted Boltzmann Machines for Combinatorial Optimization

نویسندگان

  • Malte Probst
  • Franz Rothlauf
  • Jörn Grahl
چکیده

Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Restricted Boltzmann Machines (RBMs) are generative neural networks with these desired properties. We integrate an RBM into an EDA and evaluate the performance of this system in solving combinatorial optimization problems with a single objective. We assess how the number of fitness evaluations and the CPU time scale with problem size and with problem complexity. The results are compared to the Bayesian Optimization Algorithm, a state-of-the-art EDA. Although RBM-EDA requires larger population sizes and a larger number of fitness evaluations, it outperforms BOA in terms of CPU times, in particular if the problem is large or complex. RBM-EDA requires less time for model building than BOA. These results highlight the potential of using generative neural networks for combinatorial optimization.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Study of Maximum Matching on Boltzmann Machines

The Boltzmann machine is one of the most popular neural network models used to cope with diicult combinatorial optimisation problems. It has been used to nd near optimum solutions to such hard problems as graph partitioning and the Travelling Salesman problem. However, very little is known about the time complexity of solving combinatorial optimisation problems on Boltzmann machines. This issue...

متن کامل

Simulated annealing and Boltzmann machines - a stochastic approach to combinatorial optimization and neural computing

By reading, you can know the knowledge and things more, not only about what you get from people to people. Book will be more trusted. As this simulated annealing and boltzmann machines a stochastic approach to combinatorial optimization and neural computing, it will really give you the good idea to be successful. It is not only for you to be success in certain life you can be successful in ever...

متن کامل

How to Center Binary Restricted Boltzmann Machines

It has recently been shown that subtracting the mean from the visible as well as the hidden variables of deep Boltzmann machines leads to better conditioned optimization problems and improves some aspects of model performance. In this work we analyze binary restricted Boltzmann machines, where centering is done by subtracting offset values from visible and hidden variables. We show analytically...

متن کامل

Boltzmann Machines and their Applications

In this paper we present a formal model of the Boltzmann machine and a discussion of two different applications of the model, viz. (i) solving combinatorial optimization problems and (ii) carrying out learning tasks. Numerical results of computer simulations are presented to demonstrate the characteristic features of the Boltzmann machine.

متن کامل

Combinatorial Optimization on a Boltzmann Machine

We discuss the problem of solving (approximately) combinatorial optimization problems on a Boltzmann machine. It is shown for a number of combinatorial optimization problems how they can be mapped directly onto a Boltzmann machine by choosing appropriate connection patterns and connection strengths. In this way maximizing the consensus in the Boltzmann machine is equivalent to finding an optima...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • European Journal of Operational Research

دوره 256  شماره 

صفحات  -

تاریخ انتشار 2017