arXiv subjects

Michael Doherty

Publications and source records attributed to Michael Doherty.

6 recordsLinked to original sources

arXiv2026

Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks

Reinforcement learning (RL) has been widely applied to dynamic routing, modulation and spectrum assignment (RMSA) in optical networks, yet no prior work has trained a transformer model for this task. We attribute this to the high data and compute requirements of transformers and potential training instabilities with RL. We address this gap by combining recent advances from the machine learning literature (rotary positional encodings for graph-structured data, off-policy invalid action masking, and valid mass regularization) with GPU-accelerated simulation to achieve, for the first time, stable RL training of a transformer for dynamic RMSA. We demonstrate, through systematic benchmarking against previous RL methods and heuristic algorithms, that ours is the first RL method to exceed all benchmarks, increasing the supportable traffic load by up to 13%. To demonstrate the scalability of our approach, we train on real network topologies from the TopologyBench database up to 143 nodes and 362 links, with 320 x 12.5 GHz frequency slot units per link, and 100 Gbps traffic requests. To our knowledge, these are the largest dynamic RMSA problems to which RL has been applied. We find up to 4% increased traffic load can be supported at low blocking probability (<0.1%) with our method compared to the best available benchmark algorithm. We present an ablation study of the components of our training algorithm, the dynamics of the loss function during training, and analyze the allocation decisions of the trained models. We make all code used to produce this paper openly available for reproduction and future benchmarking: https://github.com/micdoh/XLRON.

cs.NI↗

arXiv2026

Fast stabilizer state preparation via AI-optimized graph decimation

We propose a general method for preparing stabilizer states with reduced two-qubit gate count and depth compared to the state of the art. The method starts from a graph state representation of the stabilizer state and iteratively reduces the number of edges in the graph using two-qubit Clifford gates to produce a unitary preparation circuit. We explore various heuristic search and AI-based approaches to optimally choose Clifford gates at each step, the most sophisticated of which is a combination of reinforcement learning and Monte Carlo tree search that we call QuSynth. We apply our method to synthesize code states of various quantum error correcting codes including the 23-qubit Golay code and the 144-qubit gross code, the latter of which is significantly beyond the qubit number that is accessible to prior optimal circuit synthesis methods. We demonstrate that our techniques are capable of reducing the required two-qubit gates by up to a factor of 2.5 compared to previous approaches while retaining low circuit depth.

quant-ph↗

arXiv2025

Reinforcement Learning with Graph Attention for Routing and Wavelength Assignment with Lightpath Reuse

Many works have investigated reinforcement learning (RL) for routing and spectrum assignment on flex-grid networks but only one work to date has examined RL for fixed-grid with flex-rate transponders, despite production systems using this paradigm. Flex-rate transponders allow existing lightpaths to accommodate new services, a task we term routing and wavelength assignment with lightpath reuse (RWA-LR). We re-examine this problem and present a thorough benchmarking of heuristic algorithms for RWA-LR, which are shown to have 6% increased throughput when candidate paths are ordered by number of hops, rather than total length. We train an RL agent for RWA-LR with graph attention networks for the policy and value functions to exploit the graph-structured data. We provide details of our methodology and open source all of our code for reproduction. We outperform the previous state-of-the-art RL approach by 2.5% (17.4 Tbps mean additional throughput) and the best heuristic by 1.2% (8.5 Tbps mean additional throughput). This marginal gain highlights the difficulty in learning effective RL policies on long horizon resource allocation tasks.

cs.NI↗

arXiv2025

Reinforcement Learning for Dynamic Resource Allocation in Optical Networks: Hype or Hope?

The application of reinforcement learning (RL) to dynamic resource allocation in optical networks has been the focus of intense research activity in recent years, with almost 100 peer-reviewed papers. We present a review of progress in the field, and identify significant gaps in benchmarking practices and reproducibility. To determine the strongest benchmark algorithms, we systematically evaluate several heuristics across diverse network topologies. We find that path count and sort criteria for path selection significantly affect the benchmark performance. We meticulously recreate the problems from five landmark papers and apply the improved benchmarks. Our comparisons demonstrate that simple heuristics consistently match or outperform the published RL solutions, often with an order of magnitude lower blocking probability. Furthermore, we present empirical lower bounds on network blocking using a novel defragmentation-based method, revealing that potential improvements over the benchmark heuristics are limited to 19-36% increased traffic load for the same blocking performance in our examples. We make our simulation framework and results publicly available to promote reproducible research and standardized evaluation https://doi.org/10.5281/zenodo.12594495.

cs.NI↗

arXiv2024

Topology Bench: Systematic Graph Based Benchmarking for Core Optical Networks

Topology Bench is a comprehensive topology dataset designed to accelerate benchmarking studies in optical networks. The dataset, focusing on core optical networks, comprises publicly accessible and ready-to-use topologies, including (a) 105 georeferenced real-world optical networks and (b) 270,900 validated synthetic topologies. Prior research on real-world core optical networks has been characterised by fragmented open data sources and disparate individual studies. Moreover, previous efforts have notably failed to provide synthetic data at a scale comparable to our present study. Topology Bench addresses this limitation, offering a unified resource and represents a 61.5% increase in spatially-referenced real world optical networks. To benchmark and identify the fundamental nature of optical network topologies through the lens of graph-theoretical analysis, we analyse both real and synthetic networks using structural, spatial and spectral metrics. Our comparative analysis identifies constraints in real optical network diversity and illustrates how synthetic networks can complement and expand the range of topologies available for use. Currently, topologies are selected based on subjective criteria, such as preference, data availability, or perceived suitability, leading to potential biases and limited representativeness. Our framework enhances the generalisability of optical network research by providing a more objective and systematic approach to topology selection. A statistical and correlation analysis reveals the quantitative range of all of these graph metrics and the relationships between them. Finally, we apply unsupervised machine learning to cluster real-world topologies into distinctive groups using nine optimal graph metrics using K-means. We conclude the analysis by providing guidance on how to use such clusters to select a diverse set of topologies for future studies.

cs.NI↗

arXiv2023

On some Impedance Boundary Conditions for a Thermo-Piezo-Electromagnetic System

Based on a combination of insights afforded by Rainer Picard and Serge Nicaise, we extend a set of abstract piezo-electromagnetic impedance boundary conditions. We achieve this by accommodating for the influence of heat with the inclusion of a new equation and additional boundary terms. We prove the evolutionary well-posedness of a known thermo-piezo-electromagnetic system under these boundary conditions. Evolutionary well-posedness here means unique solvability as well as continuous and causal dependence on given data.

math.AP↗