Stay up to date with the latest academic and research topics in the quantum community by joining our live discussions every Friday at 12PM EDT. Tune in to gain insights from experts and engage with a community of quantum enthusiasts!
Curated by: Qiskit (180 videos)
Episode 167 Title: Problem-informed Graphical Quantum Generative Learning Abstract: Leveraging the intrinsic probabilistic nature of quantum systems, generative quantum machine learning (QML) offers the potential to outperform classical learning models. Current generative QML algorithms mostly rely on general-purpose models that, while being very expressive, face several training challenges. A potential way to address these setbacks involves constructing problem-informed models capable of more efficient training on structured problems. In particular, probabilistic graphical models provide a flexible framework for representing structure in generative learning problems and can thus be exploited to incorporate inductive bias in QML algorithms. In this work, we propose a problem-informed quantum circuit Born machine Ansatz for learning the joint probability distribution of random variables, with independence relations efficiently represented by a Markov network (MN). We further demonstrate the applicability of the MN framework in constructing generative learning benchmarks and compare our model's performance to previous designs, showing it outperforms problem-agnostic circuits. Based on a preliminary analysis of trainability, we narrow down the class of MNs to those exhibiting favorable trainability properties. Finally, we discuss the potential of our model to offer quantum advantage in the context of generative learning. Bio: Zoltán Zimborás is the head of the Quantum Computing and Information Research Group at the Wigner Research Centre for Physics and also a senior researcher at Algorithmiq. He obtained his PhD at the Eötvös University in Budapest and worked later at UPV Bilbao, University College London, and Freie Universität Berlin before returning to Hungary. His fields of interests include the theoretical aspects of quantum computing as well as the practical implementation of quantum algorithms on actual quantum devices. Being a member of the steering board of World Quantum Day and of QWorld, he is involved in various outreach activities. Together with his colleagues, he developed new university courses on Quantum Computing that actively use the online available quantum computer prototypes.