Quantum Machine Learning (QML) is an emerging field that combines the power of quantum computing with the capabilities of machine learning to tackle complex problems across science and engineering. QML leverages quantum principles such as superposition, entanglement, and interference to enhance data representation and accelerate certain computational primitives in learning pipelines. This direction explores quantum-enhanced models and algorithms, ranging from variational circuits to quantum kernels, to improve performance, scalability, and robustness in practical applications.
Our interests
Our interests focus on two main directions:
- Applying and benchmarking established QML methods on machine learning tasks: We study and implement quantum machine learning approaches that have been developed previously, apply them to standard problems such as classification, regression, reinforcement learning, and representation learning, and build fair, quantitative benchmarking pipelines to rigorously evaluate whether these QML methods offer real advantages over classical counterparts.
- Developing new quantum algorithms for ML: We investigate and propose new quantum algorithms for established ML paradigms, especially quantum reinforcement learning, aiming to exploit genuinely quantum structures to improve performance, generalization, and robustness.