607 citations · 1.2k across the 25 of their papers we have counts for
7 papers · 1 filter
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…
Contextual Text Denoising with Masked Language Models
Yifu Sun, Haoming Jiang
Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models ar…
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…
On the Variance of the Adaptive Learning Rate and Beyond
Liyuan Liu, Haoming Jiang, Pengcheng He +4
The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization a…
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…
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…