We present a novel procedure for optimization based on the combination of efficient
quantized tensor train representation and a generalized maximum matrix volume principle …

A fundamental property of deep learning normalization techniques, such as batch
normalization, is making the pre-normalization parameters scale invariant. The intrinsic …

We show the effectiveness of automatic differentiation in efficiently and correctly computing
and controlling the spectrum of implicitly linear operators, a rich family of layer types …

The vulnerability of neural network classifiers to adversarial attacks is a major obstacle to
their deployment in safety-critical applications. Regularization of network parameters during …

Transferability of adversarial examples is a well-known property that endangers all
classification models, even those that are only accessible through black-box queries. Prior …

When learning stable linear dynamical systems from data, three important properties are
desirable: i) predictive accuracy, ii) provable stability, and iii) computational efficiency …

Controlling the spectral norm of the Jacobian matrix, which is related to the convolution
operation, has been shown to improve generalization, training stability and robustness in …

We show the effectiveness of automatic differentiation in efficiently and correctly computing
and controlling the spectrum of implicitly linear operators, a rich family of layer types …

Object recognition in remote sensing is a well-developed problem in both scientific and
industrial applications. However, the limitations in computational resources often make it …