tksmatsubara / symplectic-adjoint-method
Code for "Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory," NeurIPS, 2021.
☆16Updated 3 years ago
Alternatives and similar repositories for symplectic-adjoint-method:
Users that are interested in symplectic-adjoint-method are comparing it to the libraries listed below
- Refining continuous-in-depth neural networks☆39Updated 3 years ago
- Convex potential flows☆83Updated 3 years ago
- Computing gradients and Hessians of feed-forward networks with GPU acceleration☆18Updated last year
- code for "Neural Conservation Laws A Divergence-Free Perspective".☆37Updated 2 years ago
- ☆106Updated 3 years ago
- Reference implementation of Finite Element Networks as proposed in "Learning the Dynamics of Physical Systems from Sparse Observations wi…☆70Updated 10 months ago
- Second-Order Neural ODE Optimizer, NeurIPS 2021 spotlight☆52Updated 3 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆87Updated 2 years ago
- Symplectic Recurrent Neural Networks☆28Updated 2 years ago
- This repository contains code released by DiffEqML Research☆89Updated 3 years ago
- Riemannian Optimization Using JAX☆48Updated last year
- Nonparametric Differential Equation Modeling☆53Updated last year
- Experiments from the paper "On Second Order Behaviour in Augmented Neural ODEs"☆58Updated 6 months ago
- ☆39Updated last year
- Code for the paper "Rational neural networks", NeurIPS 2020☆28Updated 4 years ago
- Code for efficiently sampling functions from GP(flow) posteriors☆72Updated 4 years ago
- Repo to the paper "Lie Point Symmetry Data Augmentation for Neural PDE Solvers"☆49Updated last year
- Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.☆75Updated last month
- Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting☆45Updated last year
- Source code for Large-Scale Wasserstein Gradient Flows (NeurIPS 2021)☆32Updated 2 years ago
- By introducing a differentiable contact model, DiffCoSim extends the applicability of Lagrangian/Hamiltonian-inspired neural networks to …☆34Updated 2 years ago
- Wraps PyTorch code in a JIT-compatible way for JAX. Supports automatically defining gradients for reverse-mode AutoDiff.☆49Updated last month
- LieTransformer: Equivariant Self-Attention for Lie Groups☆69Updated 8 months ago
- ☆21Updated 5 months ago
- Stochastic Normalizing Flows☆76Updated 3 years ago
- ☆45Updated 4 years ago
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- Neural Stochastic PDEs: resolution-invariant modelling of continuous spatiotemporal dynamics☆51Updated 2 years ago
- ☆46Updated last year
- [ICML 2022] Learning Efficient and Robust Ordinary Differential \\ Equations via Invertible Neural Networks☆10Updated last year