Neural Ordinary Differential Equations
cs.LG, cs.AI, stat.ML
Submitted: 2018-06-19
Updated: 2026-10-09
Comments: v6: Corrected Fig. 3c function-evaluation counts (thanks to Vanni et al.); typo fixes
Code: https://github.com/rtqichen/torchdiffeq
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Sylvester Normalizing Flows for Variational Inference
- The Stan Math Library: Reverse-Mode Automatic Differentiation in C++
- Reversible Architectures for Arbitrarily Deep Residual Neural Networks
- NICE: Non-linear Independent Components Estimation
- Adaptive Computation Time for Recurrent Neural Networks
- HyperNetworks
- Variable Computation in Recurrent Neural Networks
- Adam: A Method for Stochastic Optimization
- Time-Dependent Representation for Neural Event Sequence Prediction
- Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
- Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
- Variational Inference with Normalizing Flows
- Deep Neural Networks Motivated by Partial Differential Equations
- Reliable Decision Support using Counterfactual Models
- Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions
- Improving Variational Auto-Encoders using Householder Flow
- Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks