Primal Dual

Primal-dual methods are optimization techniques that solve problems by iteratively updating both primal and dual variables, aiming to find a saddle point satisfying both the objective function and constraints. Current research focuses on improving the efficiency and robustness of these methods, particularly through adaptive algorithms that eliminate the need for line searches and handle non-Euclidean norms, as well as extensions to federated learning and constrained reinforcement learning settings. These advancements are significant for tackling large-scale optimization problems in diverse fields, including machine learning, control systems, and network optimization, leading to improved algorithm performance and broader applicability.

Papers

June 17, 2024

Constrained Reinforcement Learning with Average Reward Objective: Model-Based and Model-Free Algorithms
Vaneet Aggarwal, Washim Uddin Mondal, Qinbo Bai
Reinforcement Learning Primal Dual Constrained Reinforcement Learning Constrained Markov Decision Process Average Reward Markov Decision Process Model Free Algorithm Average Reward

June 14, 2024

A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
Liuyuan Jiang, Quan Xiao, Victor M. Tenorio, Fernando Real-Rojas, Antonio G. Marques, Tianyi Chen
Bilevel Optimization Optimization Problem Primal Dual Gradient Based Algorithm Coupled Linear Constraint

May 29, 2024

May 25, 2024

Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Federico Fusco
Primal Dual Stochastic Way O$ Regret Best of Both World Algorithm Adversarial Constraint Regret Minimizer

May 23, 2024

Doubly-Dynamic ISAC Precoding for Vehicular Networks: A Constrained Deep Reinforcement Learning (CDRL) Approach
Zonghui Yang, Shijian Gao, Xiang Cheng
Constructive Approach Primal Dual Vehicular Network Integrated Sensing and Communication Constrained Deep Reinforcement Learning

May 17, 2024

Sample-Efficient Constrained Reinforcement Learning with General Parameterization
Washim Uddin Mondal, Vaneet Aggarwal
Primal Dual Constrained Markov Decision Process Global Optimality Momentum Acceleration

May 9, 2024

Learning to Slice Wi-Fi Networks: A State-Augmented Primal-Dual Approach
Yiğit Berkay Uslu, Roya Doostnejad, Alejandro Ribeiro, Navid NaderiAlizadeh
LeArning Abstract Primal Dual Quality of Service Cellular Network Network Slicing Model Slicing

May 6, 2024

Federated Reinforcement Learning with Constraint Heterogeneity
Hao Jin, Liangyu Zhang, Zhihua Zhang
Policy Gradient Proximal Policy Optimization Primal Dual Federated Reinforcement Learning Natural Policy Gradient Heterogeneity Challenge

May 3, 2024

Continuous Learned Primal Dual
Christina Runkel, Ander Biguri, Carola-Bibiane Schönlieb
Diffusion Model Inverse Problem Neural ODE Neural Ordinary Differential Equation Primal Dual Numerical Discretization

April 25, 2024

A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints
Bram De Cooman, Johan Suykens
Reinforcement Learning Primal Dual Model Free Reinforcement Learning Multiple View Actor Critic Reinforcement Learning Policy Constraint

April 6, 2024

Demand Balancing in Primal-Dual Optimization for Blind Network Revenue Management
Sentao Miao, Yining Wang
Primal Dual Optimal Regret Regret Analysis Supply Demand Nonparametric Instrumental Variable Network Revenue Management

March 19, 2024

Primal Methods for Variational Inequality Problems with Functional Constraints
Liang Zhang, Niao He, Michael Muehlebach
Primal Dual Variational Inequality Lagrange Multiplier Constrained Gradient

March 5, 2024

Reconstruction for Sparse View Tomography of Long Objects Applied to Imaging in the Wood Industry
Buda Bajić, Johannes A. J. Huber, Benedikt Neyses, Linus Olofsson, Ozan Öktem
Full State Reconstruction X Ray Sparse View Primal Dual Tree Specie Imaging Technique Tomographic Reconstruction Iterative Reconstruction Surface Parameterization Large Object

February 24, 2024

Truly No-Regret Learning in Constrained MDPs
Adrian Müller, Pragnya Alatur, Volkan Cevher, Giorgia Ramponi, Niao He
Regret Bound Primal Dual Sublinear Regret Constrained Markov Decision Process Primal Dual Algorithm

February 16, 2024

Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning
Zihao Li, Boyi Liu, Zhuoran Yang, Zhaoran Wang, Mengdi Wang
Markov Decision Process Low Rank Primal Dual Constrained Reinforcement Learning Strong Duality Convex Constraint

February 14, 2024

Low-Rank Extragradient Methods for Scalable Semidefinite Optimization
Dan Garber. Atara Kaplan
Primal Dual Semidefinite Programming Complementarity Constraint Positive Semidefinite Stochastic Extragradient Extragradient Method

February 13, 2024

Primal-Dual Algorithms with Predictions for Online Bounded Allocation and Ad-Auctions Problems
Eniko Kevi, Nguyen Kim Thang
Human Prediction Primal Dual Ad Auction Online Allocation Matching Problem

February 3, 2024

Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
Qinbo Bai, Washim Uddin Mondal, Vaneet Aggarwal
Optimal Policy Primal Dual Constrained Markov Decision Process Regret Guarantee Simple Regret Policy Gradient Algorithm Average Reward Markov Decision Process Policy Parametrization

February 1, 2024

Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
Zakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee, Carola-Bibiane Schönlieb
Inverse Problem Early Stage Convergence Regularization Model Primal Dual Variational Regularization Convex Regularization Convex Neural Network Critical Point Convergent Regularization

Primal Dual

Papers

Constrained Reinforcement Learning with Average Reward Objective: Model-Based and Model-Free Algorithms

A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints

One-Shot Safety Alignment for Large Language Models via Optimal Dualization

Rotation Averaging: A Primal-Dual Method and Closed-Forms in Cycle Graphs

Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints

Doubly-Dynamic ISAC Precoding for Vehicular Networks: A Constrained Deep Reinforcement Learning (CDRL) Approach

Sample-Efficient Constrained Reinforcement Learning with General Parameterization

Learning to Slice Wi-Fi Networks: A State-Augmented Primal-Dual Approach

Federated Reinforcement Learning with Constraint Heterogeneity

Continuous Learned Primal Dual

A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints

Demand Balancing in Primal-Dual Optimization for Blind Network Revenue Management

Primal Methods for Variational Inequality Problems with Functional Constraints

Reconstruction for Sparse View Tomography of Long Objects Applied to Imaging in the Wood Industry

Truly No-Regret Learning in Constrained MDPs

Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning

Low-Rank Extragradient Methods for Scalable Semidefinite Optimization

Primal-Dual Algorithms with Predictions for Online Bounded Allocation and Ad-Auctions Problems

Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm

Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation