Protocol for implementing quantum nonparametric learning with trapped ions
This work addresses the computational bottleneck in machine learning for researchers by offering a quantum speedup, though it is incremental as it builds on existing quantum methods.
The authors tackled the problem of nonparametric learning by proposing a quantum paradigm that achieves an exponential speedup over sample size, demonstrating a feasible implementation with trapped ions.
Nonparametric learning is able to make reliable predictions by extracting information from similarities between a new set of input data and all samples. Here we point out a quantum paradigm of nonparametric learning which offers an exponential speedup over the sample size. By encoding data into quantum feature space, similarity between the data is defined as an inner product of quantum states. A quantum training state is introduced to superpose all data of samples, encoding relevant information for learning in its bipartite entanglement spectrum. We demonstrate that a trained state for prediction can be obtained by entanglement spectrum transformation, using quantum matrix toolbox. We further work out a feasible protocol to implement the quantum nonparametric learning with trapped ions, and demonstrate the power of quantum superposition for machine learning.