TinyUDE: Solver-Free Universal Differential Equations on Microcontrollers via Lie-Taylor Jet Matching
cs.LG, cs.ET
Submitted: 2026-09-22
Updated: 2026-09-22
Terminology
Sources
- Universal Differential Equations for Scientific Machine Learning
- TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems
- MCUNet: Tiny Deep Learning on IoT Devices
- On-Device Training Under 256KB Memory
- Adam: A Method for Stochastic Optimization
- Latent ODEs for Irregularly-Sampled Time Series
- Augmented Neural ODEs
- On Neural Differential Equations
- Hamiltonian Neural Networks
- Lagrangian Neural Networks
- Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
- ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
- Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows
- MLPerf Tiny Benchmark
- Automatic differentiation in machine learning: a survey
- SGDR: Stochastic Gradient Descent with Warm Restarts
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks