Nonconvex Constraint

Nonconvex constraint optimization addresses the challenge of finding optimal solutions within complex, non-linearly defined feasible regions. Current research focuses on developing efficient algorithms, such as those based on proximal augmented Lagrangian methods, normalizing flows, and first-order optimization with expansive projections, to handle these constraints in various applications, including reinforcement learning, federated learning, and optimal control problems. These advancements are crucial for solving real-world problems where constraints are inherently nonconvex, improving the performance and feasibility of solutions in diverse fields like robotics, machine learning, and resource allocation. The development of single-loop algorithms offers a significant improvement in computational efficiency compared to previous multi-loop approaches.

Papers

February 7, 2024

FlowPG: Action-constrained Policy Gradient with Normalizing Flows
Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat Kumar
Reinforcement Learning Policy Gradient Normalizing Flow Hamiltonian Monte Carlo Nonconvex Constraint

October 16, 2023

Federated Learning with Convex Global and Local Constraints
Chuan He, Le Peng, Ju Sun
Federated Learning Convex Function Constrained Learning Convex Constraint Nonconvex Constraint

September 30, 2023

May 26, 2023

Optimizing NOTEARS Objectives via Topological Swaps
Chang Deng, Kevin Bello, Bryon Aragam, Pradeep Ravikumar
Non Convex Optimization Problem Swap Distance Minimization Nonconvex Constraint

July 17, 2022

Robust Action Governor for Uncertain Piecewise Affine Systems with Non-convex Constraints and Safe Reinforcement Learning
Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky
Safe Reinforcement Learning Control Constraint Piecewise Affine Nonconvex Constraint

July 12, 2022

A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
Songtao Lu
General Nonconvex Primal Dual Algorithm Smooth Nonconvex Functional Constrained Optimization Nonconvex Constraint

June 12, 2022

Federated Learning on Riemannian Manifolds
Jiaxiang Li, Shiqian Ma
Optimization Purpose Riemannian Manifold Riemannian Counterpart Nonconvex Constraint