Differentiable Implicit Layers
arXiv:2010.07078
Abstract
In this paper, we introduce an efficient backpropagation scheme for non-constrained implicit functions. These functions are parametrized by a set of learnable weights and may optionally depend on some input; making them perfectly suitable as a learnable layer in a neural network. We demonstrate our scheme on different applications: (i) neural ODEs with the implicit Euler method, and (ii) system identification in model predictive control.
References in corpus (10)
- Deep Equilibrium Models
- Differentiable MPC for End-to-end Planning and Control
- Differentiable Convex Optimization Layers
- Task-based End-to-end Model Learning in Stochastic Optimization
- Generative Adversarial Imitation from Observation
- Nonsymmetric multigrid preconditioning for conjugate gradient methods
- Neural Networks with Cheap Differential Operators
- Infinite-Horizon Differentiable Model Predictive Control
- Implicitly Defined Layers in Neural Networks
- Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability