A General Framework for Machine Learning based Optimization Under Uncertainty

12/21/2021
by   Philipp A. Guth, et al.
0

We propose a general framework for machine learning based optimization under uncertainty. Our approach replaces the complex forward model by a surrogate, e.g., a neural network, which is learned simultaneously in a one-shot sense when solving the optimal control problem. Our approach relies on a reformulation of the problem as a penalized empirical risk minimization problem for which we provide a consistency analysis in terms of large data and increasing penalty parameter. To solve the resulting problem, we suggest a stochastic gradient method with adaptive control of the penalty parameter and prove convergence under suitable assumptions on the surrogate model. Numerical experiments illustrate the results for linear and nonlinear surrogate models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2020

Consistency analysis of bilevel data-driven learning in inverse problems

One fundamental problem when solving inverse problems is how to find reg...
research
03/03/2022

Adaptive machine learning based surrogate modeling to accelerate PDE-constrained optimization in enhanced oil recovery

In this contribution, we develop an efficient surrogate modeling framewo...
research
11/03/2018

Biconvex Landscape In SDP-Related Learning

Many machine learning problems can be reduced to learning a low-rank pos...
research
12/23/2021

A general framework for penalized mixed-effects multitask learning with application on DNAm biomarkers creation

The creation of non invasive biomarkers from blood DNA methylation profi...
research
10/14/2017

Arbitrage-Free Regularization

We introduce a path-dependent geometric framework which generalizes the ...
research
10/24/2021

A deep learning based surrogate model for stochastic simulators

We propose a deep learning-based surrogate model for stochastic simulato...
research
08/30/2023

Domain Generalization without Excess Empirical Risk

Given data from diverse sets of distinct distributions, domain generaliz...

Please sign up or login with your details

Forgot password? Click here to reset