Personal tools
You are here: Home Events ANC Workshop: Arno Onken and Arturs Bekasovs, Chair: Kai Xu

ANC Workshop: Arno Onken and Arturs Bekasovs, Chair: Kai Xu

— filed under:

  • ANC Workshop Talk
When Nov 27, 2018
from 11:00 AM to 12:00 PM
Where IF 4.31/4.33
Add event to calendar vCal

Arno Onken

Title: Non-parametric copula-based information estimation


Estimation of mutual information has become indispensable in many fields but is complicated by its dependence on the characteristics of the underlying probability distributions. Here we propose a non-parametric copula-based information estimator which exploits a close relationship between the copula framework and mutual information. The resulting estimator is applicable to both continuous and discrete variables. We validate our method on artificial samples drawn from various statistical distributions and show that our estimator compares favourably with alternative estimators in a wide range of situations. In particular, we show that our estimator strikes a good balance between general applicability to various dependence structures and the number of samples required for robust information estimates.


Arturs Bekasovs

Title: Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting

Abstract: Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversarial points, but careful analysis is problematic due to the complexity of these models. Recently Gilmer et al. (2018) introduced adversarial spheres, a toy set-up that simplifies both practical and theoretical analysis of the problem. In this work we use the adversarial sphere set-up to understand the properties of approximate Bayesian inference methods for a linear model in a noiseless setting. We compare predictions of Bayesian and non-Bayesian methods, showcasing the advantages of the former, although revealing open challenges for deep learning applications.