In the age of artificial intelligence, the best approach to handling huge amounts of data is a
tremendously motivating and hard problem. Among machine learning models, stochastic …

Deep classifier neural networks enter the terminal phase of training (TPT) when training
error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural …

The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

Recently, pure transformer-based models have shown great potentials for vision tasks such
as image classification and detection. However, the design of transformer networks is …

The emerging paradigm of federated learning (FL) strives to enable collaborative training of
deep models on the network edge without centrally aggregating raw data and hence …

There is mounting evidence of emergent phenomena in the capabilities of deep learning
methods as we scale up datasets, model sizes, and training times. While there are some …

We formally study how ensemble of deep learning models can improve test accuracy, and
how the superior performance of ensemble can be distilled into a single model using …

In the past decade the mathematical theory of machine learning has lagged far behind the
triumphs of deep neural networks on practical challenges. However, the gap between theory …

We identify and formalize a fundamental gradient descent phenomenon resulting in a
learning proclivity in over-parameterized neural networks. Gradient Starvation arises when …

The prospect of achieving quantum advantage with quantum neural networks (QNNs) is
exciting. Understanding how QNN properties (for example, the number of parameters M) …