Despite their remarkable achievement, gigantic transformers encounter significant
drawbacks, including exorbitant computational and memory footprints during training, as …

We systematize the approach to the investigation of deep neural network landscapes by
basing it on the geometry of the space of implemented functions rather than the space of …

Semi-supervised learning (SSL) provides methods to improve model performance through
unlabeled samples. In medical image analysis, the challenges of multi-category …

The presence of label noise in the training data has a profound impact on the generalization
of deep neural networks (DNNs). In this study, we introduce and theoretically demonstrate a …

Artificial Intelligence (AI) applications are rapidly growing, and more applications are joining
the market competition. As a result, the AI-as-a-service (AIaaS) model is experiencing rapid …

We propose an optimistic estimate to evaluate the best possible fitting performance of
nonlinear models. It yields an optimistic sample size that quantifies the smallest possible …

Transformers have shown impressive capabilities across various tasks, but their
performance on compositional problems remains a topic of debate. In this work, we …

Deep learning models have achieved an impressive performance in a variety of tasks, but
they often suffer from overfitting and are vulnerable to adversarial attacks. Previous research …

Models with nonlinear architectures/parameterizations such as deep neural networks
(DNNs) are well known for their mysteriously good generalization performance at …

Previous research has shown that fully-connected networks with small initialization and
gradient-based training methods exhibit a phenomenon known as condensation during …