Bit-bit encoding, optimizer-free training and sub-net initialization: techniques for scalable quantum machine learning

TL;DR

This paper introduces scalable quantum machine learning techniques that include binary encoding, optimizer-free training, and sub-net initialization, addressing data loading, optimization, and barren plateau issues for larger models.

Contribution

It proposes a comprehensive framework combining binary encoding, parameter-by-parameter training, and sub-net initialization to improve scalability and training efficiency in quantum machine learning.

Findings

Quantum classifiers with binary encoding can handle high-dimensional data efficiently.

Optimizer-free training guarantees convergence for quantum models when updating one parameter at a time.

Models with more qubits and parameters show consistent loss reduction across datasets.

Abstract

Quantum machine learning for classical data is currently perceived to have a scalability problem due to (i) a bottleneck at the point of loading data into quantum states, (ii) the lack of clarity around good optimization strategies, and (iii) barren plateaus that occur when the model parameters are randomly initialized. In this work, we propose techniques to address all of these issues. First, we present a quantum classifier that encodes both the input and the output as binary strings which results in a model that has no restrictions on expressivity over the encoded data but requires fast classical compression of typical high-dimensional datasets to only the most predictive degrees of freedom. Second, we show that if one parameter is updated at a time, quantum models can be trained without using a classical optimizer in a way that guarantees convergence to a local minimum, something not possible for classical deep learning models. Third, we propose a parameter initialization strategy called sub-net initialization to avoid barren plateaus where smaller models, trained on more compactly encoded data with fewer qubits, are used to initialize models that utilize more qubits. Along with theoretical arguments on efficacy, we demonstrate the combined performance of these methods on subsets of the MNIST dataset for models with an all-to-all connected architecture that use up to 16 qubits in simulation. This allows us to conclude that the loss function consistently decreases as the capability of the model, measured by the number of parameters and qubits, increases, and this behavior is maintained for datasets of varying complexity. Together, these techniques offer a coherent framework for scalable quantum machine learning.