Robust Decision

Robust decision-making focuses on developing methods that yield reliable and consistent outcomes even under uncertainty or adversarial conditions. Current research emphasizes improving the robustness of deep learning models, particularly through techniques like adversarial training and chance-constrained imitation learning, as well as developing novel algorithms such as actor-critic methods for handling unreliable data streams and calibrating model outputs for improved generalization. These advancements are crucial for deploying AI systems in high-stakes applications like autonomous driving and resource management, where reliable performance is paramount, and for enhancing the trustworthiness and safety of machine learning models in general.

Papers

November 4, 2024

Shortcut Learning in In-Context Learning: A Survey
Rui Song, Yingji Li, Fausto Giunchiglia, Hao Xu
Timely Survey Strong Generalization Context Learning Shortcut Learning Shortcut Feature Robust Decision

October 11, 2024

Robust Offline Policy Learning with Observational Data from Multiple Sources
Aldo Gael Carranza, Susan Athey
Bandit Feedback Regret Analysis Source Table Observational Data Robust Offline Reinforcement Learning Robust Decision

June 26, 2024

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Jonas Ngnawé, Sabyasachi Sahoo, Yann Pequignot, Frédéric Precioso, Christian Gagné
Adversarial Attack Native Robustness Adversarial Vulnerability Robust Decision Margin Consistency

May 8, 2024

Novel Actor-Critic Algorithm for Robust Decision Making of CAV under Delays and Loss of V2X Data
Zine el abidine Kherroubi
Autonomous Vehicle Actor Critic Algorithm Autonomous Driving System Significant Delay Change Robust Decision

January 13, 2024

COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy
Lu Wang, Mayukh Das, Fangkai Yang, Chao Duo, Bo Qiao, Hang Dong, Si Qin, Chetan Bansal, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
Reinforcement Learning Imitation Learning Adaptive Policy Common Coin Robust Decision

December 19, 2023

Learning Deterministic Surrogates for Robust Convex QCQPs
Egon Peršak, Miguel F. Anjos
Decision Focused Learning Surrogate Modelling Context Optimization Robust Decision Robust Optimisation

June 23, 2023

Adversarial Robustness Certification for Bayesian Neural Networks
Matthew Wicker, Andrea Patane, Luca Laurenti, Marta Kwiatkowska
Native Robustness Bayesian Neural Network Probabilistic Robustness Robust Decision

June 9, 2023

Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
Ezgi Korkmaz, Jonah Brown-Cohen
Reinforcement Learning Adversarial Attack Deep Reinforcement Learning Adversarial Perspective Robust Decision Adversarial Direction Stable Policy

August 20, 2022

On Robustness in Nonconvex Optimization with Application to Defense Planning
Johannes O. Royset
Native Robustness Application Proficiency Robust Optimization Mixed Integer Nonconvex Optimization Robust Decision

July 19, 2022

Holistic Robust Data-Driven Decisions
Amine Bennouna, Bart Van Parys
Model Overfitting Robust Decision

May 20, 2022

Prototypical Calibration for Few-shot Learning of Language Models
Zhixiong Han, Yaru Hao, Li Dong, Yutao Sun, Furu Wei
Language Model Context Learning Shot Classification Different Cluster Robust Decision Prototypical Calibration