Abstract
Multi-photon interference is the resource most native to photonic quantum machine learning, yet experiments on photonic reservoirs have reported advantages, null results, and train-only effects. These outcomes cannot be compared: each measures task-dependent accuracy on different tasks and platforms. Here we resolve the question task-independently through the kernel geometry of boson-sampling feature maps. Interference redistributes feature variance across roughly twice as many effective dimensions as distinguishable-particle statistics, generating a large geometric separation between the corresponding kernels. The separation grows superlinearly with indistinguishability, is linear in Hong--Ou--Mandel visibility at small visibility for two to four photons, and retains approximately 80% of its magnitude at the source quality of current quantum processors. Under experimental sampling budgets the separation is learnable on adversarially constructed tasks (accuracy advantage +0.22 plus or minus 0.05) and an order of magnitude smaller on natural tasks, gated by kernel--task alignment. The results reconcile the existing experimental record and supply a pre-experimental protocol: kernel geometry establishes that an interference-specific learning resource exists, and task alignment determines whether a given task can access it; both are computable before committing significant hardware resources.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kar, O., & H, A. B. (2026). When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing. https://omanscience.com/en/articles/when-does-interference-help-learning-kernel-geometry-as-a-pre-experimental-test-for-photonic-reservoir-computing
MLA 9
Kar, Oishik, and Aswath Babu H. "When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing." https://omanscience.com/en/articles/when-does-interference-help-learning-kernel-geometry-as-a-pre-experimental-test-for-photonic-reservoir-computing.
Chicago (author–date)
Kar, Oishik, and Aswath Babu H. 2026. "When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing." https://omanscience.com/en/articles/when-does-interference-help-learning-kernel-geometry-as-a-pre-experimental-test-for-photonic-reservoir-computing.
Harvard
Kar, O. and H, A. B. (2026) 'When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing', Available at: https://omanscience.com/en/articles/when-does-interference-help-learning-kernel-geometry-as-a-pre-experimental-test-for-photonic-reservoir-computing.
Vancouver
Kar O, H AB. When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing. https://omanscience.com/en/articles/when-does-interference-help-learning-kernel-geometry-as-a-pre-experimental-test-for-photonic-reservoir-computing
IEEE
O. Kar, and A. B. H, "When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing," https://omanscience.com/en/articles/when-does-interference-help-learning-kernel-geometry-as-a-pre-experimental-test-for-photonic-reservoir-computing.