Robust Optimization

Robust optimization aims to find solutions that remain optimal even when faced with uncertainty in data or model parameters, a crucial consideration in many real-world applications. Current research focuses on developing efficient algorithms, such as stochastic primal-dual methods and those leveraging techniques from sleeping bandits, to solve increasingly complex robust optimization problems, particularly those involving non-convex loss functions and high-dimensional data. These advancements are improving the robustness and reliability of machine learning models across diverse fields, including network traffic classification, robotics, and financial modeling, by mitigating the impact of data imbalances, adversarial attacks, and model uncertainty. The development of tractable formulations and efficient algorithms is a key driver of progress in this active area of research.

Papers

November 4, 2024

Distributionally Robust Optimization
Daniel Kuhn, Soroosh Shafiee, Wolfram Wiesemann
Robust Optimization Distributionally Robust Optimization Structural Ambiguity Operation Research Intrinsic Uncertainty

November 2, 2024

Federated Learning with Relative Fairness
Shogo Nakakita, Tatsuya Kaneko, Shinya Takamaeda-Yamazaki, Masaaki Imaizumi
Federated Learning Convergence Rate Robust Optimization Fairness Objective Proportional Fairness Fairness Criterion

October 28, 2024

$\texttt{skwdro}$: a library for Wasserstein distributionally robust machine learning
Florian Vincent, Waïss Azizian, Franck Iutzeler, Jérôme Malick
Machine Learning Pytorch Model Robust Optimization Easy to Use Library Wasserstein Dictionary First Choice Maximality Robust Robot Robust Objective

October 21, 2024

Enhancing PAC Learning of Half spaces Through Robust Optimization Techniques
Shirmohammad Tavangari, Zahra Shakarami, Aref Yelghi, Asef Yelghi
Robust Version Robust Optimization Barzilai Borwein Technique Adversarial Scenario PAC Learning Margin Halfspaces Learning Halfspaces Noise Resistant Property

October 17, 2024

October 8, 2024

Communication-Efficient Federated Group Distributionally Robust Optimization
Zhishuai Guo, Tianbao Yang
Robust Optimization Distributionally Robust Optimization

October 1, 2024

Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
Quan Nguyen, Nishant A. Mehta, Cristóbal Guzmán
Sample Complexity Sparsity Increase Robust Optimization Distributionally Robust Optimization Novel Concept Minimax Rate

September 28, 2024

Group Distributionally Robust Optimization can Suppress Class Imbalance Effect in Network Traffic Classification
Wumei Du, Qi Wang, Yiqin Lv, Dong Liang, Guanlin Wu, Xingxing Liang, Zheng Xie
Class Imbalance Robust Optimization Decision Boundary Distributionally Robust Optimization Traffic Classification

September 12, 2024

Wasserstein Distributionally Robust Multiclass Support Vector Machine
Michael Ibrahim, Heraldo Rozas, Nagi Gebraeel
Robust Optimization Multiclass Classification Non Linear Label Ambiguity Wasserstein Distributionally Robust

September 5, 2024

A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization
Aron Brenner, Rahman Khorramfar, Jennifer Sun, Saurabh Amin
Native Robustness Robust Optimization Contingency Game Generative Deep Learning Approach Capacity Expansion

August 26, 2024

Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning
Joey Hejna, Chethan Bhateja, Yichen Jian, Karl Pertsch, Dorsa Sadigh
Foundation Model Imitation Learning Robust Optimization Action Localization Robotic Datasets Data Mixture Manipulation Datasets

August 22, 2024

Zeroth-Order Stochastic Mirror Descent Algorithms for Minimax Excess Risk Optimization
Zhihao Gu, Zi Xu
Robust Optimization Excess Risk Minimax Optimization Problem Stochastic Mirror Descent

August 19, 2024

Unsupervised Machine Learning Hybrid Approach Integrating Linear Programming in Loss Function: A Robust Optimization Technique
Andrew Kiruluta, Andreas Lemos
Machine Learning Loss Function Optimization Problem Robust Optimization Linear Programming Unsupervised Machine Learning

August 5, 2024

RCDM: Enabling Robustness for Conditional Diffusion Model
Weifeng Xu, Xiang Zhu, Xiaoyong Li
Diffusion Model Native Robustness Conditional Diffusion Model Robust Optimization

July 31, 2024

Distributionally Robust Optimization as a Scalable Framework to Characterize Extreme Value Distributions
Patrick Kuiper, Ali Hasan, Wenhao Yang, Yuting Ng, Hoda Bidkhori, Jose Blanchet, Vahid Tarokh
Robust Optimization Distributionally Robust Optimization Semi Parametric Extreme Value Theory Alpha Stable Multivariate Extreme

July 26, 2024

HERO-SLAM: Hybrid Enhanced Robust Optimization of Neural SLAM
Zhe Xin, Yufeng Yue, Liangjun Zhang, Chenming Wu
Simultaneous Localization and Mapping Simultaneous Localization Robust Optimization

July 23, 2024

Data-driven Multistage Distributionally Robust Linear Optimization with Nested Distance
Rui Gao, Rohit Arora, Yizhe Huang
Convex Optimization Robust Optimization Dynamic Programming Distributionally Robust Optimization Robust Evaluation Optimal Robust Policy

July 22, 2024

Robust personalized pricing under uncertainty of purchase probabilities
Shunnosuke Ikeda, Naoki Nishimura, Noriyoshi Sukegawa, Yuichi Takano
High Uncertainty Anticipation Robust Version Robust Optimization Curious Price Large Scale Optimization Personalized Pricing

July 19, 2024

An Uncertainty-aware Deep Learning Framework-based Robust Design Optimization of Metamaterial Units
Zihan Wang, Anindya Bhaduri, Hongyi Xu, Liping Wang
Robust Optimization Simple Structure Metamaterial Unit Surrogate Based Mechanical Metamaterials Uncertainty Aware Deep Learning

Robust Optimization

Papers

Distributionally Robust Optimization

Federated Learning with Relative Fairness

$\texttt{skwdro}$: a library for Wasserstein distributionally robust machine learning

Enhancing PAC Learning of Half spaces Through Robust Optimization Techniques

Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization

From Distributional Robustness to Robust Statistics: A Confidence Sets Perspective

Communication-Efficient Federated Group Distributionally Robust Optimization

Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity

Group Distributionally Robust Optimization can Suppress Class Imbalance Effect in Network Traffic Classification

Wasserstein Distributionally Robust Multiclass Support Vector Machine

A Deep Generative Learning Approach for Two-stage Adaptive Robust Optimization

Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning

Zeroth-Order Stochastic Mirror Descent Algorithms for Minimax Excess Risk Optimization

Unsupervised Machine Learning Hybrid Approach Integrating Linear Programming in Loss Function: A Robust Optimization Technique

RCDM: Enabling Robustness for Conditional Diffusion Model

Distributionally Robust Optimization as a Scalable Framework to Characterize Extreme Value Distributions

HERO-SLAM: Hybrid Enhanced Robust Optimization of Neural SLAM

Data-driven Multistage Distributionally Robust Linear Optimization with Nested Distance

Robust personalized pricing under uncertainty of purchase probabilities

An Uncertainty-aware Deep Learning Framework-based Robust Design Optimization of Metamaterial Units