6 citations · 16 across the 6 of their papers we have counts for
6 papers
High Probability Convergence of Clipped-SGD Under Heavy-tailed Noise
Ta Duy Nguyen, Thien Hang Nguyen, Alina Ene +1
While the convergence behaviors of stochastic gradient methods are well understood \emph{in expectation}, there still exist many gaps in the understanding of their convergence with…
High Probability Convergence of Stochastic Gradient Methods
Zijian Liu, Ta Duy Nguyen, Thien Hang Nguyen +2
In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous w…
META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions
Zijian Liu, Ta Duy Nguyen, Thien Hang Nguyen +2
We study the application of variance reduction (VR) techniques to general non-convex stochastic optimization problems. In this setting, the recent work STORM [Cutkosky-Orabona '19]…
Improved Group Robustness via Classifier Retraining on Independent Splits
Thien Hang Nguyen, Hongyang R. Zhang, Huy Le Nguyen
Deep neural networks trained by minimizing the average risk can achieve strong average performance. Still, their performance for a subgroup may degrade if the subgroup is underrepr…
Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings
Linlin Liu, Thien Hai Nguyen, Shafiq Joty +2
Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddi…
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
Bosheng Ding, Linlin Liu, Lidong Bing +5
Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high q…