Search Results for author:
Found 9 papers, 2 papers with code
On Generation of Adversarial Examples using Convex Programming
Moreover, this framework is capable of explaining various existing adversarial methods and can be used to derive new algorithms as well.
Sensing Matrix Design and Sparse Recovery on the Sphere and the Rotation Group
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
Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization
Considered as a data-driven approach, Fingerprinting Localization Solutions (FPSs) enjoy huge popularity due to their good performance and minimal environment information requirement.
A Discontinuous Neural Network for Non-Negative Sparse Approximation
It is shown that the presented network converges to equilibrium points which are solutions to general non-negative least squares optimization problems.
Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples
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.
On the Trajectory of Stochastic Gradient Descent in the Information Plane
Studying the evolution of information theoretic quantities during Stochastic Gradient Descent (SGD) learning of Artificial Neural Networks (ANNs) has gained popularity in recent years.
A Tensor Analysis on Dense Connectivity via Convolutional Arithmetic Circuits
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.
On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks
In this work, this problem is studied through the lens of compression which is captured by the low-rank structure of weight matrices.
Adversarial Risk Bounds for Neural Networks through Sparsity based Compression
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.
