We study the impact of dependence uncertainty on the expectation of the
...
Federated Learning (FL) is a popular distributed machine learning paradi...
Graph contrastive learning (GCL), as an emerging self-supervised learnin...
Graph Neural Networks (GNNs), which aggregate features from neighbors, a...
Recent studies show that despite achieving high accuracy on a number of
...
Counterfactual (CF) explanations for machine learning (ML) models are
pr...
Federated learning is a machine learning training paradigm that enables
...
Past literature has illustrated that language models do not fully unders...
Owing much to the revolution of information technology, the recent progr...
"Benign overfitting", where classifiers memorize noisy training data yet...
Due to the explosion in the size of the training datasets, distributed
l...
This paper proposes a novel asymmetric copula based upon bivariate split...
Adversarial training is currently the most powerful defense against
adve...
Adversarial training is so far the most effective strategy in defending
...
Deep neural networks are vulnerable to adversarial attacks. Among differ...
Starting with Gilmer et al. (2018), several works have demonstrated the
...
Depending on how much information an adversary can access to, adversaria...
Adaptive gradient methods, which adopt historical gradient information t...
We present a unified framework to analyze the global convergence of Lang...
We consider the phase retrieval problem of recovering the unknown signal...
We propose a nonconvex estimator for joint multivariate regression and
p...