Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
TAM 1.2.5 documentation
Logo
TAM 1.2.5 documentation

🚀 Getting Started

  • TAM (Time series Additive Model)
  • 📚 Theory Introduction of TAM and Cheatsheet

🧠 Theory: The Core Engine

  • The Exact Primal Resolution
  • The Theory of N-Dim Broadcasting and Normalization
  • Linear Algebra: Direct vs. Iterative Solvers
  • Computational Complexity (\(\mathcal{O}(D^3+T D^2)\) vs \(\mathcal{O}(T^3)\))
  • Hyperparameter Optimization: Generalized Cross-Validation (GCV)

🌈 Theory: The Spectrum Library

  • The Linear Effect (Ridge Regression)
  • The Spline Effect (P-Splines)
  • The Fourier Effect (Sobolev Spectral Basis)
  • The Wavelet Effect (Ricker)
  • The Chebyshev Effect (Polynomial Minimax Basis)
  • The Tree Effect (Random Forests & Binning Features)
  • The Neural Effect (NEPT)
  • The Radial Basis Function (RBF) Effect
  • The Categorical Effect (Discrete Topologies)
  • The Tensor Product Effect (Interactions)
  • Physics-Informed Kernel Learning (PIKL)
  • The PID Effect (Autoregressive Control Dynamics)
  • The Linear Tree Effect (Varying-Coefficient Models)

⚙️ Theory: Meta-Learners & Inference

  • Adaptive Online Learning (AdaptiveTAM)
  • Dynamic Tracking via Extended Kalman Filtering [BETA]
  • Hierarchical Joint Optimization [BETA]
  • Uncertainty Quantification via Conformal Prediction [EXP]
  • Online Prediction by Expert Aggregation (OPERA)
  • Deep-GAM Hybridization and Orthogonal Backfitting [EXP]
  • Statistical Inference and Diagnostics (Glass-Box) [EXP]
  • Evolutionary Orchestration and Multi-Fidelity AutoML
  • AutoTAM Data Topology and Structural Safeguards [EXP]
  • Empirical Evaluation and MLOps Diagnostics

💻 Architecture: Core Implementation

  • The Additive API and Object-Oriented Architecture
  • The Engineering of Normalization and Padding
  • PyTorch Math Dispatcher & Matrix-Free Solvers
  • Hardware Memory Dispatch & Anti-OOM Systems
  • Auto-ML via Generalized Cross-Validation (GCV)
  • The Spectral Dictionary: PyTorch Implementations & Factory Assembly

🛠️ Architecture: Advanced Orchestration

  • Online Error Correction (AdaptiveTAM)
  • Kalman TorchScript Optimizations & Block Updates [BETA]
  • Hierarchical Engineering & Memory Assembly [BETA]
  • Diagnostics, Visualization & Utilities Engineering [EXP]
  • OPERA GPU Tensor Batching
  • DeepGAM Engineering & Sequential Encapsulation [EXP]
  • Diagnostics, Visualization & Utilities Engineering [EXP]
  • Orchestrator Pipeline and Evolutionary Hub-and-Spoke Engine [EXP]
  • AutoTAM Data Topology: Stateful Architecture & Pandas Vectorization [EXP]
  • MLOps Tracking and Empirical Benchmarking (Engineering)

🧪 Gallery of Examples & Use Cases

  • 🧪 Gallery of Examples & Use Cases

📚 References & Changelog

  • 👥 Authors and Contributions
  • 🔬 Scientific Background & Acknowledgments
  • Changelog
  • 🤝 Contributing to Time series Additive Model (TAM)
  • 📘 Documentation Generation Guide (TAM)
  • References
Back to top
View this page

🧪 Gallery of Examples & Use Cases¶

⬅️ README | 📚 THEORY

This chapter showcases the versatility of the TAM framework. It maps the Python scripts provided in use_cases/ to specific theoretical challenges, ensuring every advanced feature (Kalman, Neural, Hierarchy, Safety) is illustrated.

🚀 How to run: All examples are independant you can launch them with those commands from the project root :

python readme.py
python cheatsheet.py
python air_passengers.py
python paper_reproductions/2011_pierrot_goude.py
python paper_reproductions/2025_doumeche_et_al.py
Next
👥 Authors and Contributions
Previous
MLOps Tracking and Empirical Benchmarking (Engineering)
Copyright © 2026, Yann Allioux, Nathan Doumèche, Éloi Bedek
Made with Sphinx and @pradyunsg's Furo