5 papers
"Train classical, deploy quantum" requires rethinking generalization
Snehal Raj, Natansh Mathur, Alejandro Perdomo-Ortiz
Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum generative models are considered…
Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy
Snehal Raj, Brian Coyle, Léo Monbroussou +3
Graphs provide a natural language for relational data in chemistry, biology and optimisation. Graph neural networks (GNNs) have driven much of the recent progress in learning from…
Adaptive directional gradients for parameterised quantum circuits
Brian Coyle, Snehal Raj, Virag Umathe +2
Training parameterised quantum circuits (PQCs) on quantum hardware is bottlenecked by the measurement cost of gradient estimation, which under the parameter-shift rule scales linea…
Bayesian Quantum Orthogonal Neural Networks for Anomaly Detection
Natansh Mathur, Brian Coyle, Nishant Jain +4
Identification of defects or anomalies in 3D objects is a crucial task to ensure correct functionality. In this work, we combine Bayesian learning with recent developments in quant…
QuIC: Quantum-Inspired Compound Adapters for Parameter Efficient Fine-Tuning
Snehal Raj, Brian Coyle
Scaling full finetuning of large foundation models strains GPU memory and training time. Parameter Efficient Fine-Tuning (PEFT) methods address this issue via adapter modules which…