7 papers
Scaling Behavior of Parameterized Quantum Circuits from a Lie-Algebraic Perspective
Hiroshi Ohno
Understanding how the performance of parameterized quantum circuits scales with available resources is important for characterizing their trainability and effective model capacity.…
Lie-Group Mode Connectivity in Quantum Machine Learning from a Dynamical Lie Algebra Perspective
Hiroshi Ohno
Mode connectivity has been widely studied in classical machine learning as a geometric property of low-loss regions in parameter space. In quantum machine learning (QML), however,…
A regularization method for quantum neural networks using data symmetry
Hiroshi Ohno
Leveraging data symmetries has recently become a key strategy in quantum neural networks (QNNs) to improve training efficiency. In this study, we propose a symmetry-informed regula…
Rademacher Complexity Bounds for Parameterized Quantum Circuits Generated by Pauli Strings
Hiroshi Ohno
In this study, we analyze the Rademacher complexity of a parameterized unitary whose generators are chosen from -qubit Pauli strings. Although generalizati…
Observable-Guided Generator Selection for Improving Trainability in Quantum Machine Learning with a -Purity Interpretation under Restricted Settings
Hiroshi Ohno
To study generator design for parameterized unitaries in quantum machine learning (QML), we propose an observable-guided generator selection algorithm for -qubit Pauli-string…
Approximate Cosine Similarity Estimation via an Angle-Encoding Hadamard Test
Hiroshi Ohno
The Hadamard test is a standard quantum primitive for estimating inner products and expectation values, but in data-processing settings its practical utility is often limited by th…