Can we learn gradients by Hamiltonian Neural Networks?
Not on the map. Why?
Abstract (arXiv)
In this work, we propose a meta-learner based on ODE neural networks that learns gradients. This approach makes the optimizer is more flexible inducing an automatic inductive bias to the given task. Using the simplest Hamiltonian Neural Network we demonstrate that our method outperforms a meta-learner based on LSTM for an artificial task and the MNIST dataset with ReLU activations in the optimizee. Furthermore, it also surpasses the classic optimization methods for the artificial task and achieves comparable results for MNIST.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 18 references that are in the map. First posted on arXiv 31 Oct 2021.
Builds on
7 of 18 references.
References · 7
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2016An overview of gradient descent optimization algorithmscited by 1,033
- 2016Learning to learn by gradient descent by gradient descentcited by 620
- 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 184
- 2020Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learningcited by 79
- 2019Port-Hamiltonian Approach to Neural Network Trainingcited by 4
Built on by
Not cited yet.