Adversarial Estimator

Adversarial estimators are a class of statistical methods that leverage a minimax optimization framework, pitting an estimator against an "adversary" that attempts to find weaknesses in the estimation process. Current research focuses on applications in causal inference, robust model training (particularly against adversarial attacks and data perturbations), and dimensionality reduction, often employing neural networks to enhance model flexibility and representation power. These methods offer improved robustness and efficiency in various settings, leading to advancements in areas such as generalized linear models, reinforcement learning, and generative modeling, with implications for both theoretical understanding and practical applications.

Papers

May 7, 2024

Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning
Yihong Gu, Cong Fang, Peter Bühlmann, Jianqing Fan
Heterogeneous Environment Causal Categorization Invariance Learning Data Driven Causal Adversarial Estimator

January 27, 2024

Asymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation
Yiling Xie, Xiaoming Huo
Adversarial Attack Adversarial Training Asymptotic Behavior Adaptive Adversarial Training Adversarial Estimator

December 11, 2023

Adversarial Estimation of Topological Dimension with Harmonic Score Maps
Eric Yeats, Cameron Darwin, Frank Liu, Hai Li
Topological Feature Manifold Learning Manifold Dimension Local Intrinsic Dimension Estimation Adversarial Estimator

October 30, 2023

Towards Practical Non-Adversarial Distribution Matching
Ziyu Gong, Ben Usman, Han Zhao, David I. Inouye
Adversarial Loss Distribution Matching Adversarial Estimator Adversarial Matching Method

October 10, 2023

Bi-Level Offline Policy Optimization with Limited Exploration
Wenzhuo Zhou
Offline Reinforcement Learning Policy Optimization Regret Guarantee Offline Policy Pure Exploration Bellman Error Adversarial Estimator

September 2, 2023

Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models
Changyu Liu, Yuling Jiao, Junhui Wang, Jian Huang
Adversarial Loss Non Asymptotic Model Misspecification Adversarial Risk Adversarial Estimator

July 19, 2023

Adversarial Likelihood Estimation With One-Way Flows
Omri Ben-Dov, Pravir Singh Gupta, Victoria Abrevaya, Michael J. Black, Partha Ghosh
Generative Adversarial Network GAN Model Adversarial Framework Wasserstein Gan Adversarial Estimator Bidirectional Flow

July 1, 2023

Hiding in Plain Sight: Differential Privacy Noise Exploitation for Evasion-resilient Localized Poisoning Attacks in Multiagent Reinforcement Learning
Md Tamjid Hossain, Hung La
Differential Privacy Poisoning Attack Plain Sight Differential Privacy Noise Adversarial Estimator

April 22, 2022

Adversarial Estimators
Jonas Metzger
Maximum Likelihood Linear Estimator Neural Estimator Adversarial Estimator Truncated M Estimator