32 citations · 204 across the 33 of their papers we have counts for
10 papers · 1 filter
Pruning vs Quantization: Which is Better?
Andrey Kuzmin, Markus Nagel, Mart van Baalen +2
Neural network pruning and quantization techniques are almost as old as neural networks themselves. However, to date only ad-hoc comparisons between the two have been published. In…
A PAC-Bayesian Generalization Bound for Equivariant Networks
Arash Behboodi, Gabriele Cesa, Taco Cohen
Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relate…
Quantized Sparse Weight Decomposition for Neural Network Compression
Andrey Kuzmin, Mart van Baalen, Markus Nagel +1
In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is comput…
Equivariant Priors for Compressed Sensing with Unknown Orientation
Anna Kuzina, Kumar Pratik, Fabio Valerio Massoli +1
In compressed sensing, the goal is to reconstruct the signal from an underdetermined system of linear measurements. Thus, prior knowledge about the signal of interest and its struc…
Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks
Ekkehard Schnoor, Arash Behboodi, Holger Rauhut
Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measureme…
Gradient Regularization for Quantization Robustness
Milad Alizadeh, Arash Behboodi, Mart van Baalen +3
We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-trainin…
Adversarial Risk Bounds for Neural Networks through Sparsity based Compression
Emilio Rafael Balda, Arash Behboodi, Niklas Koep +1
Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under attacks. To comba…
On the Effect of Low-Rank Weights on Adversarial Robustness of Neural Networks
Peter Langenberg, Emilio Rafael Balda, Arash Behboodi +1
Recently, there has been an abundance of works on designing Deep Neural Networks (DNNs) that are robust to adversarial examples. In particular, a central question is which features…
Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples
Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs o…
On Generation of Adversarial Examples using Convex Programming
Emilio Rafael Balda, Arash Behboodi, Rudolf Mathar
It has been observed that deep learning architectures tend to make erroneous decisions with high reliability for particularly designed adversarial instances. In this work, we show…