Y
Yaoliang Yu
Researcher at University of Waterloo
Publications - 113
Citations - 3338
Yaoliang Yu is an academic researcher from University of Waterloo. The author has contributed to research in topics: Robustness (computer science) & Estimator. The author has an hindex of 25, co-authored 111 publications receiving 2742 citations. Previous affiliations of Yaoliang Yu include Fudan University & Carnegie Mellon University.
Papers
More filters
Journal ArticleDOI
Petuum: A New Platform for Distributed Machine Learning on Big Data
Eric P. Xing,Qirong Ho,Wei Dai,Jin-Kyu Kim,Jinliang Wei,Seunghak Lee,Xun Zheng,Pengtao Xie,Abhimanu Kumar,Yaoliang Yu +9 more
TL;DR: This work proposes a general-purpose framework, Petuum, that systematically addresses data- and model-parallel challenges in large-scale ML, by observing that many ML programs are fundamentally optimization-centric and admit error-tolerant, iterative-convergent algorithmic solutions.
Journal ArticleDOI
Semantic Pooling for Complex Event Analysis in Untrimmed Videos
TL;DR: This work defines a novel notion of semantic saliency that assesses the relevance of each shot with the event of interest and proposes a new isotonic regularizer that is able to exploit the constructed semantic ordering information.
Posted Content
Petuum: A New Platform for Distributed Machine Learning on Big Data
Eric P. Xing,Qirong Ho,Wei Dai,Jin-Kyu Kim,Jinliang Wei,Seunghak Lee,Xun Zheng,Pengtao Xie,Abhimanu Kumar,Yaoliang Yu +9 more
TL;DR: In this article, the authors propose a general-purpose framework that systematically addresses data and model-parallel challenges in large-scale ML, by observing that many ML programs are fundamentally optimization-centric and admit error-tolerant, iterative-convergent algorithmic solutions.
Proceedings Article
Convex Multi-view Subspace Learning
TL;DR: This paper develops an efficient algorithm that recovers an optimal data reconstruction by exploiting an implicit convex regularizer, then recovers the corresponding latent representation and reconstruction model, jointly and optimally.
Proceedings ArticleDOI
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
TL;DR: This work proposes a simple but effective method, DeeBERT, to accelerate BERT inference, which allows samples to exit earlier without passing through the entire model, and provides new ideas to efficiently apply deep transformer-based models to downstream tasks.