Simulated annealing is applied for deep learning using convolutional neural networks. Likewise, can quantum annealing be used?

These two papers:

have both used the annealing technique for optimization of the problems but with different learning types. Therefore, my concern is whether quantum annealing can be applied for convolutional neural networks as well as or not.

If yes, then how? If no, then why not?

Any reference or related theories or work will be a great help.

  • $\begingroup$ Hi, Aasish. Welcome to Quantum Computing SE! Please note that it's good etiquette to link to the abstract of a paper rather than the PDF version. Also, use appropriate tags for your questions. Please review How to write a good question? I've edited your question this time but it would be quite annoying for us to do it on your behalf every time. $\endgroup$ Jan 8, 2019 at 9:11
  • $\begingroup$ Thanks @Blue for the edit. Yes, I am learning. $\endgroup$ Jan 8, 2019 at 9:15

1 Answer 1


I will assume you are asking about D-Wave's quantum annealer.

If there is a part of the learning process that can fit the QUBO (Quadratic Unconstrained Binary Optimization) formulation, then yes.

The problem however is what to consider as binary variables of your problem. In CNN, we have in general real-valued parameters that we tweak for training (using Stochastic Gradient Descent for instance). At first glance, considering the cost function would not fit the requirements, especially because you have nonlinear functions applied to the real weights so it does not look like a QUBO.

The second paper you mention used it especially because the energy function of Restricted Boltzmann machines is a QUBO and they were using the machine as a Boltzmann-like sampler for estimating an intractable part in the gradient (the negative part). So it's a different setup than CNNs.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.