This paper studies the use of a machine learning-based estimator as a co...
The optimal design of experiments typically involves solving an NP-hard
...
Learning mappings between infinite-dimensional function spaces has achie...
Although overparameterized models have shown their success on many machi...
Adversarial examples, which are usually generated for specific inputs wi...
In this paper, we study the statistical limits in terms of Sobolev norms...
In this paper, we study the statistical limits of deep learning techniqu...
Neural collapse is a highly symmetric geometric pattern of neural networ...
Training deep neural networks with stochastic gradient descent (SGD) can...
Distillation is a method to transfer knowledge from one model to another...
The Transformer architecture is widely used in natural language processi...
Deep learning achieves state-of-the-art results in many areas. However r...
Deep learning achieves state-of-the-art results in many areas. However r...
Missing data recovery is an important and yet challenging problem in ima...
Partial differential equations (PDEs) are commonly derived based on empi...
In this paper, we propose a new control framework called the moving endp...
In our work, we bridge deep neural network design with numerical differe...
In this paper, we present an initial attempt to learn evolution PDEs fro...