mlsanityData to 14 Oct 2026

LCAP: Population-Informed Latent Chip Adaptation from Few Output Probes for Photonic Neural Networks

arXiv 2609.16823 ↗First posted 15 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Photonic neural networks (PNNs) offer efficient analog inference, but parameters optimized under ideal device models can degrade after fabrication, creating a persistent simulation-to-hardware (sim-to-real) gap. When many identically designed chips are deployed, calibrating each device from scratch compounds this cost. We propose Latent Chip Adaptation from Probes (LCAP), a population-informed framework that decomposes hardware adaptation into a transferable population correction and probe-inferred latent personalization. LCAP first learns a shared correction from 80 historical chips, then extracts a low-dimensional correction space from device-specific refinements. At deployment, 32 fixed unlabeled output probes infer an unseen chip's latent correction coordinates, enabling feed-forward personalization without target-device optimization. On a three-layer 64-mode MZI simulator with phase variation, beam-splitter errors, quantization, and crosstalk, accuracy improves from 80.4147% under direct deployment to 92.6860% after shared calibration and 93.3617% with LCAP. LCAP improves 27/30 unseen chips and raises worst-device accuracy from 89.18% to 90.54%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 15 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

5 of 15 references.

References · 5

  1. 2020Photonics for artificial intelligence and neuromorphic computingcited by 112
  2. 2018Training of photonic neural networks through in situ backpropagationcited by 45
  3. 2021L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimizationcited by 21
  4. 2022Dual adaptive training of photonic neural networkscited by 9
  5. 2022Characterizing Coherent Integrated Photonic Neural Networks under Imperfectionscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning
  2. 2026Constrained Co-Design for Photonic Bayesian Neural Networks
  3. 2026Inverse-designed meta processing units for multi-task near-field photonic computing
  4. 2024Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment
  5. 2026When Every Simulation Counts: Value-Based Reinforcement Learning for Accelerated Photonics Inverse Design
  6. 2024TeMPO: Efficient Time-Multiplexed Dynamic Photonic Tensor Core for Edge AI with Compact Slow-Light Electro-Optic Modulator
  7. 2025Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits
  8. 2022NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation