Meta-Learning-Based Adaptive Hyperparameter Tuning for Nonlinear Compensation in Optical Transmission
Abstract To break the nonlinear Shannon capacity bottleneck, next-generation coherent systems are widely adopting probabilistic constellation shaping (PCS) and ultra-wideband multiplexing. However, these critically exacerbate nonlinear impairments. While neural network-based nonlinear equalizers (NNLEs) offer a promising mitigation path, their practical deployment is fundamentally crippled by the prohibitive manual overhead and fragile convergence of hyperparameter tuning (HT). We introduce a meta-learning-based adaptive HT framework (MAHT) that breaks this barrier by establishing a differentiable co-optimization across training dynamics and data rebalancing, enabling NNLEs to self-adapt without human intervention. We experimentally demonstrate an S+C+L-band DP-PCS-128QAM transmission over 150 km fiber, attaining an achievable information rate (AIR) of 215.35 Tbps. Moreover, MAHT delivers exceptional weight efficiency, outperforming conventional methods by nearly 150%, and automatically optimizes across multiple channels. This work establishes a self-optimizing, resource-efficient paradigm that bridges machine learning with practical high-speed optical networks, paving the way for truly autonomous transceiver systems.
Authors
- Zicai Cao (ORCID: https://orcid.org/0009-0003-2518-1872)
- Lei Deng (ORCID: https://orcid.org/0000-0003-2647-4610)
- Mengfan Cheng (ORCID: https://orcid.org/0000-0002-8221-0612)
- Ming Tang (ORCID: https://orcid.org/0000-0001-8669-4186)
- Ziheng Zhang (ORCID: https://orcid.org/0009-0002-9786-7155)
- Deming Liu (ORCID: https://orcid.org/0000-0001-5591-2929)
- Xiangyu Xie
Institutions
- Huazhong University of Science and Technology (CN)
Publication Details
- Journal
- Research Square
- Published
- 2026-11-12
- DOI
- https://doi.org/10.21203/rs.3.rs-10362749/v1
- Primary Topic
- Optical Network Technologies
- Type
- preprint