490 citations · 1.5k across the 111 of their papers we have counts for
9 papers · 1 filter
On Generalization Bounds of a Family of Recurrent Neural Networks
Minshuo Chen, Xingguo Li, Tuo Zhao
Recurrent Neural Networks (RNNs) have been widely applied to sequential data analysis. Due to their complicated modeling structures, however, the theory behind is still largely mis…
Towards Understanding the Importance of Shortcut Connections in Residual Networks
Tianyi Liu, Minshuo Chen, Mo Zhou +3
Residual Network (ResNet) is undoubtedly a milestone in deep learning. ResNet is equipped with shortcut connections between layers, and exhibits efficient training using simple fir…
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
Haoming Jiang, Pengcheng He, Weizhu Chen +3
Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text…
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing
Haoming Jiang, Chen Liang, Chong Wang +1
Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks a…
Towards Understanding the Importance of Noise in Training Neural Networks
Mo Zhou, Tianyi Liu, Yan Li +3
Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largel…
Meta Learning with Relational Information for Short Sequences
Yujia Xie, Haoming Jiang, Feng Liu +2
This paper proposes a new meta-learning method -- named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from s…
Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks : Function Approximation and Statistical Recovery
Minshuo Chen, Haoming Jiang, Wenjing Liao +1
Real world data often exhibit low-dimensional geometric structures, and can be viewed as samples near a low-dimensional manifold. This paper studies nonparametric regression of Höl…
Inductive Bias of Gradient Descent based Adversarial Training on Separable Data
Yan Li, Ethan X. Fang, Huan Xu +1
Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unex…
On Scalable and Efficient Computation of Large Scale Optimal Transport
Yujia Xie, Minshuo Chen, Haoming Jiang +2
Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we…