Geometric Theory of Ising Machines
By: Andrew G. Moore, Zachary Richey, Isaac K. Martin
Potential Business Impact:
Maps computer problems to make them easier.
We contribute to the mathematical theory of the design of low temperature Ising machines, a type of experimental probabilistic computing device implementing the Ising model. Encoding the output of a function in the ground state of a physical system allows efficient and distributed computation, but the design of the energy function is a difficult puzzle. We introduce a diagrammatic device that allows us to visualize the decision boundaries for Ising circuits. It is then used to prove two results: (1) Ising circuits are a generalization of 1-NN classifiers with a certain special structure, and (2) Elimination of local minima in the energy landscape can be formulated as a linear programming problem.
Similar Papers
Correspondence Between Ising Machines and Neural Networks
Disordered Systems and Neural Networks
Computers can now learn faster at any temperature.
Learning Minimal Representations of Fermionic Ground States
Quantum Physics
Finds simpler ways to describe complex quantum stuff.
Towards Evolutionary Optimization Using the Ising Model
Neural and Evolutionary Computing
Finds the best answer in tricky problems.