Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control

06/22/2020
by   Ioannis Exarchos, et al.
0

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.

READ FULL TEXT

page 6

page 8

research
09/27/2019

The Differentiable Cross-Entropy Method

We study the Cross-Entropy Method (CEM) for the non-convex optimization ...
research
03/16/2017

End-to-End Learning for Structured Prediction Energy Networks

Structured Prediction Energy Networks (SPENs) are a simple, yet expressi...
research
05/01/2020

Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction

In this work, we propose a distributed algorithm for stochastic non-conv...
research
09/02/2020

Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs

This paper introduces a new formulation for stochastic optimal control a...
research
05/19/2021

Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization

While reinforcement learning (RL) is gaining popularity in energy system...
research
06/07/2023

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

We develop a principled approach to end-to-end learning in stochastic op...
research
09/01/2021

Deep ℒ^1 Stochastic Optimal Control Policies for Planetary Soft-landing

In this paper, we introduce a novel deep learning based solution to the ...

Please sign up or login with your details

Forgot password? Click here to reset