Quick Navigation
Topics
Trapped Ion Quantum Computing
Quantum Simulation
Quantum advantage in training binary neural networks
arXiv
Authors: Yidong Liao, Daniel Ebler, Feiyang Liu, Oscar Dahlsten
Year
2018
Paper ID
23699
Status
Preprint
Abstract Read
~2 min
Abstract Words
138
Citations
N/A
Abstract
The performance of a neural network for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This includes networks with binary weights, an important class of networks due to their practical hardware implementations. We therefore suggest an alternative approach to training binary neural networks. It utilizes a quantum superposition of weight configurations. We show that the quantum training guarantees with high probability convergence towards the globally optimal set of network parameters. This resolves two prominent issues of classical training: (1) the vanishing gradient problem and (2) common convergence to suboptimal network parameters. Moreover we achieve a provable polynomial---sometimes exponential---speedup over classical training for certain classes of tasks. We design an explicit training algorithm and implement it in numerical simulations.
Why This Paper Matters
- This paper contributes to the Quantum Simulation research area in the Quantum Articles archive.
- It adds a 2018 reference point for readers tracking recent quantum research.
- The performance of a neural network for a given task is largely determined by the initial calibration of the network parameters.
Paper Tools
Become a member to use research tools
Sign in to open papers, visit source links, share, cite, compare, copy DOI links, request category corrections, and build your reading list.
Show Paper arXiv Publisher Share
Cite This Paper
Copy URL
Compare
Copy DOI Add to Reading List
Category Correction Request
Category Correction Request
Help us improve classification quality by proposing a better category. Every request is reviewed by an admin.
Sign in to submit a category correction request for this paper.
Log In to SubmitReferences & Citation Signals
Community Reactions
Quick sentiment from readers on this paper.
Score:
0
Likes: 0
Dislikes: 0
Sign in to react to this paper.
Discussion & Reviews (Moderated)
Average Rating: 0.0 / 5 (0 ratings)
No written reviews yet.