QCNN layers equivariant under pixel cyclic shifts are exactly characterized as Fourier-mode multiplexers after QFT, enabling a deep network with constant expected gradient norm at initialization.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
quant-ph 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper presents a zero-padding method to make QFT block-encodings match open-boundary Toeplitz truncations of fractional Laplacians instead of periodic circulant surrogates.
citing papers explorer
-
Pixel-Translation-Equivariant Quantum Convolutional Neural Networks via Fourier Multiplexers
QCNN layers equivariant under pixel cyclic shifts are exactly characterized as Fourier-mode multiplexers after QFT, enabling a deep network with constant expected gradient norm at initialization.
-
Boundary-Aware QFT Block-Encoding of Fractional Laplacians
The paper presents a zero-padding method to make QFT block-encodings match open-boundary Toeplitz truncations of fractional Laplacians instead of periodic circulant surrogates.