Providing privacy protection has been one of the primary motivations of Federated Learning
(FL). Recently, there has been a line of work on incorporating the formal privacy notion of …

Providing generalization guarantees for modern neural networks has been a crucial task in
statistical learning. Recently, several studies have attempted to analyze the generalization …

Existing generalization bounds fail to explain crucial factors that drive the generalization of
modern neural networks. Since such bounds often hold uniformly over all parameters, they …

Various problems in computer vision and medical imaging can be cast as inverse problems.
A frequent method for solving inverse problems is the variational approach, which amounts …

There has been a growing interest in develo** data-driven, and in particular deep neural
network (DNN) based methods for modern communication tasks. These methods achieve …

Deep equilibrium models are based on implicitly defined functional relations and have
shown competitive performance compared with the traditional deep networks. Monotone …

Computing Lipschitz constants of neural networks allows for robustness guarantees in
image classification, safety in controller design, and generalization beyond the training data …

Improving adversarial robustness of neural networks remains a major challenge.
Fundamentally, training a neural network via gradient descent is a parameter estimation …

Combinations of neural ODEs with recurrent neural networks (RNN), like GRU-ODE-Bayes
or ODE-RNN are well suited to model irregularly observed time series. While those models …

Distributed stochastic gradient methods are gaining prominence in solving large-scale
machine learning problems that involve data distributed across multiple nodes. However …