Matrix product states, DMRG, and tensor train decomposition applied to high-dimensional logistics time series. Deployable on classical hardware today, with a clear path to quantum acceleration.
Full-day workshop on tensor network methods for logistics time-series modelling. Covers MPS, DMRG, and tensor train decomposition applied to multi-SKU demand sensing, IoT anomaly detection, and multi-variate forecasting on classical hardware.
Logistics data is high-dimensional and sparse. Thousands of SKUs, hundreds of correlated features (weather, promotions, traffic, supplier lead times), and irregular time-series with missing values. Standard deep learning models require large training sets that logistics organisations rarely have at the individual SKU level. Tensor network methods, originally developed for quantum many-body physics (White 1992, DMRG), offer an alternative. Matrix product states (MPS) represent high-dimensional probability distributions with parameter counts that scale linearly rather than exponentially with feature dimension. Tensor train decomposition compresses multi-variate time series while preserving the correlation structure that matters for forecasting. These methods run on standard GPUs and CPUs today. No quantum hardware is required. The quantum connection is structural: tensor networks describe the same mathematical objects as quantum circuits, and variational tensor network training on future quantum devices could accelerate model optimisation for problems where classical contraction is the bottleneck. This workshop teaches participants to build, train, and deploy tensor network models for logistics applications using the ITensor library, with rigorous comparisons against PCA, autoencoders, and LSTM baselines.
Full Day Workshop structure with scheduled breaks. Content is configurable to your organisation's data infrastructure, SKU complexity, and modelling maturity.
| # | Session | Topics |
|---|---|---|
| 1 | High-Dimensional Time Series in Logistics Why standard models struggle with sparse, correlated logistics data | |
| 2 | Tensor Network Fundamentals MPS, DMRG, and tensor train decomposition for logistics applications |
|
| Break, after 60 min | ||
| 3 | Logistics Applications of Tensor Networks Demand sensing, anomaly detection, and multi-variate forecasting |
|
| 4 | Interactive Demonstration Building a tensor network model for logistics time-series data |
|
| Break, after 90 min | ||
| 5 | Quantum Connections and Classical Deployment How tensor networks bridge quantum theory and deployable classical methods |
|
| 6 | Integration and Production Readiness Deploying tensor network models in logistics data pipelines | |
| 7 | Q&A and Action Planning | |
Workshops are designed and delivered by QSECDEF in collaboration with sector specialists. All facilitators have direct experience in both quantum technologies and logistics systems.
Workshop design and delivery
QSECDEF brings world-leading expertise in post-quantum cryptography, quantum computing strategy, and defence-grade security assessment. Our advisory membership spans 600+ organisations and 1,200+ professionals working at the intersection of quantum technologies and critical infrastructure security.
Domain expertise and operational validation
Logistics workshops are co-delivered with sector specialists who bring direct operational experience in logistics organisations. This ensures workshop content is grounded in regulatory, operational, and technical realities specific to the sector.
Sessions are configured around your data infrastructure, SKU portfolio complexity, sensor networks, and existing modelling capabilities. Get in touch to discuss requirements and schedule a date.
Contact UsQuantum technologies are evolving quickly and new developments emerge regularly. This page was last updated on 15/03/2026. For the most current information about course content and suitability for your organisation, we recommend contacting us directly.
