Interior Point Methods with Adversarial Networks

05/23/2018
by   Rafid Mahmood, et al.
0

We present a new methodology, called IPMAN, that combines interior point methods and generative adversarial networks to solve constrained optimization problems with feasible sets that are non-convex or not explicitly defined. Our methodology produces ϵ-optimal solutions and demonstrates that, when there are multiple global optima, it learns a distribution over the optimal set. We apply our approach to synthetic examples to demonstrate its effectiveness and to a problem in radiation therapy treatment optimization with a non-convex feasible set.

READ FULL TEXT
research
03/19/2022

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems

Non-convex optimization problems have various important applications, wh...
research
04/12/2021

Understanding Overparameterization in Generative Adversarial Networks

A broad class of unsupervised deep learning methods such as Generative A...
research
10/11/2022

Stochastic Constrained DRO with a Complexity Independent of Sample Size

Distributionally Robust Optimization (DRO), as a popular method to train...
research
10/22/2021

Generative Adversarial Networks for Non-Raytraced Global Illumination on Older GPU Hardware

We give an overview of the different rendering methods and we demonstrat...
research
05/31/2023

Optimal Sets and Solution Paths of ReLU Networks

We develop an analytical framework to characterize the set of optimal Re...
research
09/17/2020

Integration of AI and mechanistic modeling in generative adversarial networks for stochastic inverse problems

The problem of finding distributions of input parameters for determinist...
research
05/31/2023

A Novel Black Box Process Quality Optimization Approach based on Hit Rate

Hit rate is a key performance metric in predicting process product quali...

Please sign up or login with your details

Forgot password? Click here to reset