Nonzero-sum Adversarial Hypothesis Testing Games
Authors: Sarath Yasodharan, Patrick Loiseau
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 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. |
| Researcher Affiliation | Academia | Sarath Yasodharan Department of Electrical Communication Engineering Indian Institute of Science Bangalore 560 012, India sarath@iisc.ac.in Patrick Loiseau Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG & MPI-SWS 700 avenue Centrale Domaine Universitaire 38400 St Martin d Héres, France patrick.loiseau@inria.fr |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code used for our simulations is available at https: //github.com/sarath1789/ahtg_neurips2019. |
| Open Datasets | No | The paper describes a synthetic setup for numerical examples ( |
| Dataset Splits | No | The paper does not provide specific details on dataset splitting (e.g., percentages or counts for training, validation, or test sets). It describes setting up parameters for numerical examples but not data splits. |
| Hardware Specification | No | The paper does not provide any specific hardware details used for running the experiments or simulations. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch x.x). |
| Experiment Setup | Yes | We fix X = {0, 1} (i.e. d = 2) and each probability distribution on X is represented by the probability that it assigns to the symbol 1, and hence M1(X) is viewed as the unit interval. We fix p = 0.5. For numerical computations, we discretize the set Q into 100 equally spaced points, and we only consider deterministic threshold-based decision rules for the defender. ... For the function c(q) = |q q | with q = 0.8, Figure 1(a) shows the error exponent... from n = 10 to n = 300 in steps of 10. ... In this experiment, we consider the case where Q = [0.6, 0.9] and q = 0.9. ... for the cost function c(q) = 3|q q |. From this plot, we see that, the error exponents converge to somewhere around 0.032, whereas Λ 0(0) 0.111. |