NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
arXiv:2006.11992
Abstract
In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures. Specifically, for an objective function located at some layer in the network and parameterized by some network parameters, we employ adaptive stochastic search to perform optimization over its output. This operation is differentiable and does not obstruct the passing of gradients during backpropagation, thus enabling us to incorporate it as a component in end-to-end learning. We study the proposed optimization module's properties and benchmark it against two existing alternatives on a synthetic energy-based structured prediction task, and further showcase its use in stochastic optimal control applications.
References in corpus (17)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Solving high-dimensional partial differential equations using deep learning
- On First-Order Meta-Learning Algorithms
- Unrolled Generative Adversarial Networks
- Meta-Learning with Implicit Gradients
- Differentiable MPC for End-to-end Planning and Control
- Input Convex Neural Networks
- On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
- Universal Planning Networks
- Learning Optimal Control via Forward and Backward Stochastic Differential Equations
- Learning Deep Stochastic Optimal Control Policies using Forward-Backward SDEs
- MPC-Inspired Neural Network Policies for Sequential Decision Making
- Meta-Learning Deep Energy-Based Memory Models
- Stochastic Variational Optimization
- The Limited Multi-Label Projection Layer
- Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization
- Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs