research
∙
05/25/2023
When can Regression-Adjusted Control Variates Help? Rare Events, Sobolev Embedding and Minimax Optimality
This paper studies the use of a machine learning-based estimator as a co...
share
research
∙
11/28/2022
Synthetic Principal Component Design: Fast Covariate Balancing with Synthetic Controls
The optimal design of experiments typically involves solving an NP-hard ...
research
∙
09/28/2022
Minimax Optimal Kernel Operator Learning via Multilevel Training
Learning mappings between infinite-dimensional function spaces has achie...
research
∙
09/19/2022
Importance Tempering: Group Robustness for Overparameterized Models
Although overparameterized models have shown their success on many machi...
research
∙
06/09/2022
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks
Adversarial examples, which are usually generated for specific inputs wi...
research
∙
05/15/2022
Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent
In this paper, we study the statistical limits in terms of Sobolev norms...
research
∙
10/13/2021
Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
In this paper, we study the statistical limits of deep learning techniqu...
research
∙
10/06/2021
An Unconstrained Layer-Peeled Perspective on Neural Collapse
Neural collapse is a highly symmetric geometric pattern of neural networ...
research
∙
03/11/2020
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Training deep neural networks with stochastic gradient descent (SGD) can...
research
∙
10/02/2019
Distillation ≈ Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network
Distillation is a method to transfer knowledge from one model to another...
research
∙
06/06/2019
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
The Transformer architecture is widely used in natural language processi...
research
∙
05/02/2019
You Only Propagate Once: Accelerating Adversarial Training Using Maximal Principle
Deep learning achieves state-of-the-art results in many areas. However r...
research
∙
05/02/2019
You Only Propagate Once: Painless Adversarial Training Using Maximal Principle
Deep learning achieves state-of-the-art results in many areas. However r...
research
∙
01/28/2019
CURE: Curvature Regularization For Missing Data Recovery
Missing data recovery is an important and yet challenging problem in ima...
research
∙
11/30/2018
PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
Partial differential equations (PDEs) are commonly derived based on empi...
research
∙
05/20/2018
Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
In this paper, we propose a new control framework called the moving endp...
research
∙
10/27/2017
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
In our work, we bridge deep neural network design with numerical differe...
research
∙
10/26/2017