On the Implicit Bias in Deep-Learning Algorithms Page 1 DEEP LEARNING HAS been highly
successful in recent years and has led to dramatic improvements in multiple domains …

A potentially organizing goal of the brain and cognitive sciences is to accurately explain
domains of human intelligence as executable, neurally mechanistic models. Years of …

Data scarcity is a major challenge when training deep learning (DL) models. DL demands a
large amount of data to achieve exceptional performance. Unfortunately, many applications …

Recent works in self-supervised learning have advanced the state-of-the-art by relying on
the contrastive learning paradigm, which learns representations by pushing positive pairs, or …

The remarkable practical success of deep learning has revealed some major surprises from
a theoretical perspective. In particular, simple gradient methods easily find near-optimal …

The phenomenon of benign overfitting is one of the key mysteries uncovered by deep
learning methodology: deep neural networks seem to predict well, even with a perfect fit to …

Recent developments in multimodal training methodologies, including CLIP and ALIGN,
obviate the necessity for individual data labeling. These approaches utilize pairs of data and …

We describe the new field of the mathematical analysis of deep learning. This field emerged
around a list of research questions that were not answered within the classical framework of …

Despite the great empirical success of deep reinforcement learning, its theoretical
foundation is less well understood. In this work, we make the first attempt to theoretically …

Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
Page 1 Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two …