Pengtao Xie

Petuum: A New Platform for Distributed Machine Learning on Big Data

Eric P. Xing, Qirong Ho, +7 authors Yaoliang Yu
IEEE Trans. Big Data
2015

Integrating Document Clustering and Topic Modeling

Document clustering and topic modeling are two closely related tasks which can mutually benefit each other. Topic modeling can project documents into a topic space which facilitates effective… (More)

Multi-modal distance metric learning

Pengtao Xie, Eric P. Xing
IJCAI 2013
2013

• Bottom-up construction: first specify local conditionals, then derive joint distribution • Project data from multi-modal feature spaces into latent space • Perform distance learning in the latent… (More)

Incorporating Word Correlation Knowledge into Topic Modeling

This paper studies how to incorporate the external word correlation knowledge to improve the coherence of topic modeling. Existing topic models assume words are generated independently and lack the… (More)

Diversifying Restricted Boltzmann Machine for Document Modeling

Restricted Boltzmann Machine (RBM) has shown great effectiveness in document modeling. It utilizes hidden units to discover the latent topics and can learn compact semantic representations for… (More)

Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters

Hao Zhang, Zeyu Zheng, +7 authors Eric P. Xing
USENIX Annual Technical Conference
2017

Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly… (More)

Towards Automated ICD Coding Using Deep Learning

Haoran Shi, Pengtao Xie, Zhiting Hu, Ming Zhang, Eric P. Xing
ArXiv
2017

International Classification of Diseases(ICD) is an authoritative health care classification system of different diseases and conditions for clinical and management purposes. Considering the… (More)

On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization

Recently diversity-inducing regularization methods for latent variable models (LVMs), which encourage the components in LVMs to be diverse, have been studied to address several issues involved in… (More)

Crypto-Nets: Neural Networks over Encrypted Data

Pengtao Xie, Mikhail Bilenko, Tom Finley, Ran Gilad-Bachrach, Kristin E. Lauter, Michael Naehrig
ArXiv
2014

The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a… (More)

Distributed Machine Learning via Sufficient Factor Broadcasting

Pengtao Xie, Jin Kyu Kim, +4 authors Eric P. Xing
ArXiv
2014

Matrix-parametrized models, including multiclass logistic regression and sparse coding, are used in machine learning (ML) applications ranging from computer vision to computational biology. When… (More)

Filter Results:

Publication Year

Publication Type

Co-author

Journals and Conferences

Data Set Used