Quantum Machine Learning and Life Sciences Workshop
Event date: Wednesday, May 27, 2026
Event time: 8:30 a.m. to 5 p.m.
Event location: 202 and 203 Findlay Commons
Lunch is provided.
Advance registration required by Monday, May 25. Limited space.
Workshop Overview
The Quantum Machine Learning and Life Sciences Workshop is designed to bring together researchers from quantum computing, machine learning, applied mathematics, and life sciences to explore new computational paradigms for understanding complex biological systems.
Recent advances in both quantum information science and artificial intelligence are opening new opportunities for modeling, simulation, and data-driven discovery in the life sciences. At the same time, modern biomedical research is increasingly characterized by high-dimensional, multimodal, and multi-scale data, requiring fundamentally new mathematical and computational frameworks.
This workshop aims to build a focused interdisciplinary platform where these communities can interact directly, exchange ideas, and identify shared challenges and emerging opportunities. In particular, we aim to highlight how quantum-enhanced algorithms, machine learning methodologies, and mathematical modeling can be jointly leveraged to address problems in biological systems, biomedical data analysis, and disease modeling.
The program will feature invited talks from leading researchers, a panel discussion on future directions, and breakout sessions intended to stimulate deeper technical discussions and potential collaborations. A central goal of the workshop is to foster new cross-disciplinary connections that may lead to long-term research partnerships and innovative approaches at the interface of quantum science, AI, and life sciences.
Agenda
| Time | Activity |
|---|---|
| 8:30 to 9 a.m. | Breakfast and introductory remarks:
|
| 9 to 9:50 a.m. | Keynote Speaker: Xiaodi Wu, associate professor of computer science at the University of Maryland Session chair: Mahmut Kandemir, director of the ICDS Quantum Hub Title: Quantum and Quantum-Inspired Optimization for Applications in AI and HealthCare Abstract: Harnessing quantum algorithms for optimization represents a transformative frontier in both theoretical research and real-world applications. We introduce Quantum Hamiltonian Descent (QHD), a novel optimization framework derived from the path-integral formulation of dynamical systems underlying classical gradient-based methods. We establish rigorous theoretical foundations for QHD, proving an exponential quantum–classical separation in continuous oracular optimization and demonstrating its ability to solve non-convex degree-4 polynomial problems for which state-of-the-art solvers, such as Gurobi, require super-polynomial time. To address the scalability limitations of current quantum hardware, we further develop Quantum-Inspired Hamiltonian Descent (QIHD), a scalable classical counterpart to QHD that preserves its core advantages while remaining deployable on GPUs for real-world optimization tasks. We demonstrate that QIHD, beyond serving as a practical bridge toward real-world quantum optimization, already delivers substantial improvements over industrial state-of-the-art in applications including model sparsification and cancer treatment planning in radiation oncology at real-world scale. Together, QHD and QIHD—both supported by the open-source software package QHDOPT—demonstrate how quantum principles can inspire the next generation of optimization solvers and their applications. Bio: Xiaodi Wu is an Associate Professor in the Department of Computer Science and a Fellow at the Joint Center for Quantum Information and Computer Science (QuICS) at the University of Maryland, College Park. He is also an Amazon Scholar with AWS Braket. His research focuses on bridging the gap between theory and practice in quantum computing through a full-stack, software–hardware–algorithm co-design approach that integrates both theoretical study and system building. Dr. Wu is a recipient of the Sloan Research Fellowship, the NSF CAREER Award, and the AFOSR Young Investigator Program (YIP) Award. |
| 10:15 to 11:45 a.m. | Panel Discussion: Quantum Computing and Life Sciences Moderator: Jia Li, professor of statistics Panelists:
|
| 11:45 a.m. to 1 p.m. | Lunch |
| 1 to 1:50 p.m. | Keynote Speaker: Benjamin Cordier, senior computational biologist, Oregon Health and Science University Knight Cancer Institute Session chair: Xiantao Li, professor of mathematics Title: The Landscape of Quantum Learning Advantages: Frameworks for reasoning about and applying quantum machine learning methods in biomedicine Abstract:What is the current landscape of quantum learning advantages? How can we leverage quantum learning advantages in biomedicine? The current understanding of quantum machine learning and its potential advantages is nuanced and often defies simple application to learning tasks with classical data. This talk will discuss the motivation behind quantum machine learning in biomedical research and why empirical and operational learning advantages represent a key near- to medium-term goal. Frameworks for understanding, identifying, and applying quantum learning advantages in biomedicine will be discussed, alongside known limitations and future directions. |
| 2 to 3:15 p.m. | Breakout Sessions (3 groups)
|
| 3:15 to 3:30p.m. | Break |
| 3:30 to 4:20 p.m. | Keynote Speaker: Samuel Yen-Chi Chen, lead research scientist, Wells Fargo Session chair: Wenrui Hao, director of the Center for AI and Mathematical Biology Title: Adaptive Quantum AI Architectures for Scientific Discovery and Life Sciences Abstract: Quantum machine learning has attracted growing interest as a computational framework for scientific discovery, with possible applications in molecular modeling, biological dynamics, biomedical data analysis, and other complex life-science problems. However, many current quantum machine learning models still rely on fixed variational circuit structures and manually designed ansätze, limiting their adaptability across tasks and data modalities. In this talk, I will present a methodological perspective on adaptive quantum AI architectures. Rather than focusing on a single life-science application, I will discuss how quantum neural networks, quantum recurrent models, quantum fast weight programmers, differentiable quantum architecture search, and recursive quantum sequence models can be used to build more flexible learning systems. These architectures aim to generate, modulate, or search over quantum circuit parameters and structures in a task-aware manner, enabling quantum models to adapt their internal representations over time. I will connect these ideas to scientific and life-science settings where adaptive modeling is especially important, including time-series prediction, dynamical systems and data-limited learning problems. I will also discuss key challenges such as trainability, data efficiency, interpretability, benchmark design, and near-term hardware constraints. The talk will conclude with a broader vision of quantum AI as an adaptive scientific discovery engine: a system that not only uses quantum circuits as models, but also learns how to design and refine quantum representations for complex scientific problems. |
| 4:20 to 4:40 p.m. | Breakout session reports |
| 4:40 to 5 p.m. | Closing remarks from Camelia Kantor, associate director of the Huck Institutes of the Life Sciences |
This event is supported by: