Deep neural networks (DNNs) trained with the logistic loss (also known as the cross entropy
loss) have made impressive advancements in various binary classification tasks. Despite the …

The phenomenon of benign overfitting, where a predictor perfectly fits noisy training data
while attaining low expected loss, has received much attention in recent years, but still …

Overparameterized neural networks (NNs) are observed to generalize well even when
trained to perfectly fit noisy data. This phenomenon motivated a large body of work on" …

Although deep neural networks achieve tremendous success on various classification tasks,
the generalization ability drops sheer when training datasets exhibit long-tailed distributions …

The proliferation of pretrained models, as a result of advancements in pretraining
techniques, has led to the emergence of a vast zoo of publicly available models. Effectively …

This century saw an unprecedented increase of public and private investments in Artificial
Intelligence (AI) and especially in (Deep) Machine Learning (ML). This led to breakthroughs …

Random smoothing data augmentation is a unique form of regularization that can prevent
overfitting by introducing noise to the input data, encouraging the model to learn more …

Classic learning theory suggests that proper regularization is the key to good generalization
and robustness. In classification, current training schemes only target the complexity of the …

Deep neural networks and large-scale datasets have revolutionized the field of machine
learning. However, these large networks are susceptible to overfitting to label noise …

Enzyme specificity towards cofactors like NAD (P) H is crucial for applications in
bioremediation and eco-friendly chemical synthesis. Despite their role in converting …