Combining Learned Representations for Combinatorial OptimizationDownload PDF

27 Sep 2018 (modified: 21 Dec 2018)ICLR 2019 Conference Blind SubmissionReaders: Everyone
  • Abstract: We propose a new approach to combine Restricted Boltzmann Machines (RBMs) that can be used to solve combinatorial optimization problems. This allows synthesis of larger models from smaller RBMs that have been pretrained, thus effectively bypassing the problem of learning in large RBMs, and creating a system able to model a large, complex multi-modal space. We validate this approach by using learned representations to create ``invertible boolean logic'', where we can use Markov chain Monte Carlo (MCMC) approaches to find the solution to large scale boolean satisfiability problems and show viability towards other combinatorial optimization problems. Using this method, we are able to solve 64 bit addition based problems, as well as factorize 16 bit numbers. We find that these combined representations can provide a more accurate result for the same sample size as compared to a fully trained model.
  • Keywords: Generative Models, Restricted Boltzmann Machines, Transfer Learning, Compositional Learning
  • TL;DR: We use combinations of RBMs to solve number factorization and combinatorial optimization problems.
8 Replies