paper-with-me

Papers

Nonzero-sum Adversarial Hypothesis Testing Games

2019-09-28 · NeurIPS 2019 12 · Sarath Yasodharan, Patrick Loiseau

We study nonzero-sum hypothesis testing games that arise in the context of adversarial classification, in both the Bayesian as well as the Neyman-Pearson frameworks. We first show that these games admit mixed strategy Nash equilibria, and then we examine some interesting concentration phenomena of these equilibria. Our main results are on the exponential rates of convergence of classification errors at equilibrium, which are analogous to the well-known Chernoff-Stein lemma and Chernoff information that describe the error exponents in the classical binary hypothesis testing problem, but with parameters derived from the adversarial model. The results are validated through numerical experiments.

📄 PDF Abstract BibTeX arXiv:1909.13031

Code (1)

sarath1789/ahtg_neurips2019 공식 구현

Tasks

ClassificationGeneral ClassificationLEMMATwo-sample testing

Similar Papers 제목 키워드 기반

Bayesian Hypothesis Testing for Block Sparse Signal Recovery

2015-08-22 · Mehdi Korki, Hadi Zayyani, Jingxin Zhang

This letter presents a novel Block Bayesian Hypothesis Testing Algorithm (Block-BHTA) for reconstructing block sparse signals with unknown block structures. The Block-BHTA comprises the detection and recovery of the supp…

Two-sample testing

Adversarial learning for product recommendation

2020-07-07 · Joel R. Bock, Akhilesh Maewal

Product recommendation can be considered as a problem in data fusion-- estimation of the joint distribution between individuals, their behaviors, and goods or services of interest. This work proposes a conditional, coupl…

Generative Adversarial NetworkProduct RecommendationTwo-sample testing

Generalized Likelihood Ratio Test for Adversarially Robust Hypothesis Testing

2021-12-04 · Bhagyashree Puranik, Upamanyu Madhow, Ramtin Pedarsani

Machine learning models are known to be susceptible to adversarial attacks which can cause misclassification by introducing small but well designed perturbations. In this paper, we consider a classical hypothesis testing…

Testing homogeneity in dynamic discrete games in finite samples

2020-10-05 · Federico A. Bugni, Jackson Bunting, Takuya Ura

The literature on dynamic discrete games often assumes that the conditional choice probabilities and the state transition probabilities are homogeneous across markets and over time. We refer to this as the "homogeneity a…

valid

Adversarial Example Games

2020-07-01 · NeurIPS 2020 12 · Avishek Joey Bose, Gauthier Gidel, Hugo Berard, Andre Cianflone 외

The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes att…