activity
20182022
most citedUnderstanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

117 citations · 145 across the 4 of their papers we have counts for

collaborators

8 papers

econ.EM20221 cited

Synthetic Principal Component Design: Fast Covariate Balancing with Synthetic Controls

Yiping Lu, Jiajin Li, Lexing Ying +1

The optimal design of experiments typically involves solving an NP-hard combinatorial optimization problem. In this paper, we aim to develop a globally convergent and practically e…

cs.LG2022

Importance Tempering: Group Robustness for Overparameterized Models

Yiping Lu, Wenlong Ji, Zachary Izzo +1

Although overparameterized models have shown their success on many machine learning tasks, the accuracy could drop on the testing distribution that is different from the training o…

stat.ML2020

A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth

Yiping Lu, Chao Ma, Yulong Lu +2

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be hig…

stat.ML201927 cited

Distillation Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network

Bin Dong, Jikai Hou, Yiping Lu +1

Distillation is a method to transfer knowledge from one model to another and often achieves higher accuracy with the same capacity. In this paper, we aim to provide a theoretical u…

cs.LG2019117 cited

Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View

Yiping Lu, Zhuohan Li, Di He +5

The Transformer architecture is widely used in natural language processing. Despite its success, the design principle of the Transformer remains elusive. In this paper, we provide…

stat.ML2019

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

Dinghuai Zhang, Tianyuan Zhang, Yiping Lu +2

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnera…