Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications
This work addresses a key bottleneck in quantum machine learning by providing an efficient algorithm for QuGAL, which could enable quantum advantages in generative tasks, though it is incremental as it builds on existing concepts.
The paper tackles the lack of a practical learning algorithm for quantum generative adversarial learning (QuGAL) by proposing the first such algorithm, QMMW, which achieves computational complexity polynomial in training rounds and logarithmic in input size, as demonstrated through numerical experiments for entanglement testing.
The exploration of quantum algorithms that possess quantum advantages is a central topic in quantum computation and quantum information processing. One potential candidate in this area is quantum generative adversarial learning (QuGAL), which conceptually has exponential advantages over classical adversarial networks. However, the corresponding learning algorithm remains obscured. In this paper, we propose the first quantum generative adversarial learning algorithm-- the quantum multiplicative matrix weight algorithm (QMMW)-- which enables the efficient processing of fundamental tasks. The computational complexity of QMMW is polynomially proportional to the number of training rounds and logarithmically proportional to the input size. The core concept of the proposed algorithm combines QuGAL with online learning. We exploit the implementation of QuGAL with parameterized quantum circuits, and numerical experiments for the task of entanglement test for pure state are provided to support our claims.