no code implementations • 18 Mar 2020 • Aniket Anand Deshmukh, Abhimanu Kumar, Levi Boyles, Denis Charles, Eren Manavoglu, Urun Dogan
In the usual self-supervision, we learn implicit labels from the training data for a secondary task.
no code implementations • 18 Feb 2020 • Abhimanu Kumar, Aniket Anand Deshmukh, Urun Dogan, Denis Charles, Eren Manavoglu
We show faster convergence rate with valid transformations for convex as well as certain family of non-convex objectives along with the proof of convergence to the original set of optima.
no code implementations • ICML 2017 • Pengtao Xie, Yuntian Deng, Yi Zhou, Abhimanu Kumar, Yao-Liang Yu, James Zou, Eric P. Xing
The large model capacity of latent space models (LSMs) enables them to achieve great performance on various applications, but meanwhile renders LSMs to be prone to overfitting.
no code implementations • 10 Dec 2015 • Abhimanu Kumar, Shriphani Palakodety, Chong Wang, Carolyn P. Rose, Eric P. Xing, Miaomiao Wen
Online discussion forums are complex webs of overlapping subcommunities (macrolevel structure, across threads) in which users enact different roles depending on which subcommunity they are participating in within a particular time point (microlevel structure, within threads).
no code implementations • 9 Dec 2015 • Abhimanu Kumar, Pengtao Xie, Junming Yin, Eric P. Xing
We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines.
no code implementations • 26 Nov 2015 • Pengtao Xie, Jin Kyu Kim, Yi Zhou, Qirong Ho, Abhimanu Kumar, Yao-Liang Yu, Eric Xing
Matrix-parametrized models, including multiclass logistic regression and sparse coding, are used in machine learning (ML) applications ranging from computer vision to computational biology.
no code implementations • 29 Oct 2014 • Wei Dai, Abhimanu Kumar, Jinliang Wei, Qirong Ho, Garth Gibson, Eric P. Xing
As Machine Learning (ML) applications increase in data size and model complexity, practitioners turn to distributed clusters to satisfy the increased computational and memory demands.
no code implementations • 19 Sep 2014 • Pengtao Xie, Jin Kyu Kim, Yi Zhou, Qirong Ho, Abhimanu Kumar, Yao-Liang Yu, Eric Xing
Matrix-parametrized models, including multiclass logistic regression and sparse coding, are used in machine learning (ML) applications ranging from computer vision to computational biology.
no code implementations • 30 Dec 2013 • Jinliang Wei, Wei Dai, Abhimanu Kumar, Xun Zheng, Qirong Ho, Eric P. Xing
Many ML algorithms fall into the category of \emph{iterative convergent algorithms} which start from a randomly chosen initial point and converge to optima by repeating iteratively a set of procedures.
no code implementations • 30 Dec 2013 • Eric P. Xing, Qirong Ho, Wei Dai, Jin Kyu Kim, Jinliang Wei, Seunghak Lee, Xun Zheng, Pengtao Xie, Abhimanu Kumar, Yao-Liang Yu
What is a systematic way to efficiently apply a wide spectrum of advanced ML programs to industrial scale problems, using Big Models (up to 100s of billions of parameters) on Big Data (up to terabytes or petabytes)?