arXiv Machine Learning September 24, 2026 By Pranavanath Balamurali, Hrishi Kamireddy

TinyUDE: Solver-Free Universal Differential Equations on Microcontrollers via Lie-Taylor Jet Matching

Read the original on arXiv Machine Learning →

TinyUDE introduces a solver‑free training framework for Universal Differential Equations (UDEs) that fits a hybrid vector field directly to the first and second time‑derivatives of observed system states using Lie‑Taylor jet matching. The method estimates these derivatives online via Savitzky‑Golay filtering, enabling fully analytic gradients without automatic differentiation. Experiments on damped and chaotic pendulum systems show that TinyUDE matches or surpasses conventional solver‑based baselines while using less than 108 kB of static memory and achieving real‑time on‑device training on an ESP32 microcontroller.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 21

PsiLogic: Chaos-Aware Active Cancellation for Adam with a Fair Cross-Domain Benchmark

arXiv:2607. 16268v1 Announce Type: new Abstract: Adaptive optimizers such as Adam and AdamW apply the same update rule regardless of whether training is in a chaotic early phase or near convergence.

By Ali Sultonov

llms diffusion nlp benchmarks

arXiv AI

Jun 4

Curvature-aware dynamic precision approach for physics-informed neural networks

arXiv:2606. 04736v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by embedding physical laws directly into neural network training.

By Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn, Taniya Kapoor

rag benchmarks

arXiv Machine Learning

Sep 22

Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver

arXiv:2609.24021v1 Announce Type: cross Abstract: Neural operators are data-driven models that learn mappings from inputs that parameterize partial differential equations, such as spatially varying c...

By Daniel Zhengyu Huang, Andrew M. Stuart

benchmarks

Hugging Face Trending Papers

Sep 21

Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver

Neural operators are data-driven models that learn mappings from inputs that parameterize partial differential equations, such as spatially varying coefficients, initial conditions, forcing terms, bou...

benchmarks

arXiv AI

Jun 19

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

arXiv:2601. 21542v3 Announce Type: replace-cross Abstract: Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis.

By Hongxu Chen, Hongxiang Li, Zhen Wang, Long Chen

diffusion

arXiv Machine Learning

Aug 4

AOS: Adaptive Optimizer Switching via Training-State Signals for Faster Convergence and Better Generalization

arXiv:2608. 01997v1 Announce Type: new Abstract: Single-optimizer training is a poor fit for the distinct phases of deep network optimization: adaptive methods handle noisy early gradients well but overshoot flat minima, while SGD with momentum generalizes better in the late phase but converges slowly early on.

By Alok Kumar Pandey, Umang Chaturvedi, Aatish Rana, Gopi Krishna Nedanuri

benchmarks

One email a morning, machine-written

Related stories

PsiLogic: Chaos-Aware Active Cancellation for Adam with a Fair Cross-Domain Benchmark

Curvature-aware dynamic precision approach for physics-informed neural networks

Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver

Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

AOS: Adaptive Optimizer Switching via Training-State Signals for Faster Convergence and Better Generalization