Metraipolis › archive › dc_8d2828435eba

CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution — arXiv:2610.08592

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08592
License (as archived)
CC0-1.0
Archived
2026-10-07T11:41:55.105Z
SHA-256 of the archived text
a08b84d8930e3ab9e5d33f4c3f54dff051665b293c56d765a80e4dd466dd86a7
Stable URL of this page
https://metraipolis.com/documento/dc_8d2828435eba

How to cite

CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution — arXiv:2610.08592 — arXiv (en), https://arxiv.org/abs/2610.08592 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d2828435eba (Metraipolis archive dc_8d2828435eba, sha256 a08b84d8930e3ab9e5d33f4c3f54dff051665b293c56d765a80e4dd466dd86a7)
BibTeX
@misc{dc8d2828435eba,
  title = {CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution — arXiv:2610.08592},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08592},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d2828435eba; sha256 a08b84d8930e3ab9e5d33f4c3f54dff051665b293c56d765a80e4dd466dd86a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08592. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

CNet is a C++/CUDA framework for building and training deep complex-valued neural networks (CVNNs) and, more generally, for optimizing complex-valued functions by gradient descent with Wirtinger (CR-calculus) derivatives. It takes a physics-native stance: a network is a cascade of complex -- and often unitary (the DFT) -- operations acting on an amplitude vector, and classification is a Born-rule measurement $p_k = |z_k|^2 / \|z\|^2$ rather than a softmax over real logits. Every layer ships a CPU reference and a CUDA kernel checked against finite differences, and the computation graph is cloned across the batch for GPU execution. On top of the base layers we add signal-processing primitives that turn the identity conv(x,k) = IFFT(FFT(x) . FFT(k)) into a learnable complex convolutional network, together with a true-Adam optimizer and a reduced-memory inference mode. We report three studies. First, a fully complex-valued, FNet-style causal sequence model built on a new $O(N \log N)$ causal Fourier mixer -- a triangular-masked DFT evaluated by a Bluestein / chirp-z factorization: once properly tuned it matches or exceeds a parameter-matched real-valued causal FNet on character-level language modeling, reaching the real model's converged quality in under half the training steps. Second and third, bottleneck analyses on radio-modulation classification (RML2016.10a) and the Fourier phase problem of coherent-diffraction imaging, which isolate exactly where complex-valued networks still need new operators. Across all three the complex formulation provably learns the physically correct structure. Code: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Mathematical Software (cs.MS); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.08592 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:19:24.843Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).