Search Results for author: Rudolf Mathar

Found 9 papers, 2 papers with code

Adversarial Risk Bounds for Neural Networks through Sparsity based Compression

no code implementations3 Jun 2019 Emilio Rafael Balda, Arash Behboodi, Niklas Koep, Rudolf Mathar

To study how robustness generalizes, recent works assume that the inputs have bounded $\ell_2$-norm in order to bound the adversarial risk for $\ell_\infty$ attacks with no explicit dimension dependence.

On the Trajectory of Stochastic Gradient Descent in the Information Plane

no code implementations ICLR 2019 Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

Studying the evolution of information theoretic quantities during Stochastic Gradient Descent (SGD) learning of Artificial Neural Networks (ANNs) has gained popularity in recent years.

Information Plane

Sensing Matrix Design and Sparse Recovery on the Sphere and the Rotation Group

1 code implementation25 Apr 2019 Arya Bangun, Arash Behboodi, Rudolf Mathar

It is first shown that random sensing matrices, which consists of random samples of Wigner D-functions, satisfy the Restricted Isometry Property (RIP) with a proper preconditioning and can be used for sparse recovery on the rotation group.

Information Theory Information Theory

On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks

no code implementations29 Jan 2019 Peter Langenberg, Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

In this work, this problem is studied through the lens of compression which is captured by the low-rank structure of weight matrices.

Adversarial Robustness

Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples

no code implementations15 Dec 2018 Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

The framework can be used to propose novel attacks against learning algorithms for classification and regression tasks under various new constraints with closed form solutions in many instances.

Colorization General Classification

Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization

no code implementations21 Mar 2018 Linchen Xiao, Arash Behboodi, Rudolf Mathar

Considered as a data-driven approach, Fingerprinting Localization Solutions (FPSs) enjoy huge popularity due to their good performance and minimal environment information requirement.

Data Augmentation Transfer Learning

On Generation of Adversarial Examples using Convex Programming

1 code implementation9 Mar 2018 Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

Moreover, this framework is capable of explaining various existing adversarial methods and can be used to derive new algorithms as well.

General Classification

A Tensor Analysis on Dense Connectivity via Convolutional Arithmetic Circuits

no code implementations ICLR 2018 Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar

We carry out a tensor analysis on the expressive power inter-connections on convolutional arithmetic circuits (ConvACs) and relate our results to standard convolutional networks.

A Discontinuous Neural Network for Non-Negative Sparse Approximation

no code implementations21 Mar 2016 Martijn Arts, Marius Cordts, Monika Gorin, Marc Spehr, Rudolf Mathar

It is shown that the presented network converges to equilibrium points which are solutions to general non-negative least squares optimization problems.


Cannot find the paper you are looking for? You can Submit a new open access paper.