Interior Point Methods with Adversarial Networks

05/23/2018

∙

by Rafid Mahmood, et al.

∙

York University

∙

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

Interior Point Methods with Adversarial Networks

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

Understanding Overparameterization in Generative Adversarial Networks

Stochastic Constrained DRO with a Complexity Independent of Sample Size

Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals

Solving a class of non-convex min-max games using adaptive momentum methods

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

An Unsupervised Deep Unrolling Framework for Constrained Optimization Problems in Wireless Networks

Interior Point Methods with Adversarial Networks

Related Research

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

Understanding Overparameterization in Generative Adversarial Networks

Stochastic Constrained DRO with a Complexity Independent of Sample Size

Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals

Solving a class of non-convex min-max games using adaptive momentum methods

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

An Unsupervised Deep Unrolling Framework for Constrained Optimization Problems in Wireless Networks