Quantum Machine Learning: What ML Researchers Need to Know

Quantum computing is transitioning from a largely theoretical discipline to an emerging computational technology with potential implications for machine learning. This talk provides an accessible introduction to Quantum Machine Learning (QML) from the perspective of the machine learning community, requiring no prior background in quantum computing. We will explore the fundamental concepts underlying QML, including quantum data encoding, variational quantum circuits, quantum kernel methods, and hybrid quantum-classical learning models. Along the way, we will discuss representative applications in optimization, scientific discovery, natural language processing, and physics. The talk will also examine the current state of evidence for what is quantum advantage, highlighting key challenges such as noise, scalability, barren plateaus, and data-loading costs.