71 citations · 100 across the 10 of their papers we have counts for
5 papers · 1 filter
Data Transformation Insights in Self-supervision with Clustering Tasks
Abhimanu Kumar, Aniket Anand Deshmukh, Urun Dogan +2
Self-supervision is key to extending use of deep learning for label scarce domains. For most of self-supervised approaches data transformations play an important role. However, up…
Distributed Training of Deep Neural Networks with Theoretical Analysis: Under SSP Setting
Abhimanu Kumar, Pengtao Xie, Junming Yin +1
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…
Scalable Modeling of Conversational-role based Self-presentation Characteristics in Large Online Forums
Abhimanu Kumar, Shriphani Palakodety, Chong Wang +3
Online discussion forums are complex webs of overlapping subcommunities (macrolevel structure, across threads) in which users enact different roles depending on which subcommunity…
Consistent Bounded-Asynchronous Parameter Servers for Distributed ML
Jinliang Wei, Wei Dai, Abhimanu Kumar +3
In distributed ML applications, shared parameters are usually replicated among computing nodes to minimize network overhead. Therefore, proper consistency model must be carefully c…
Petuum: A New Platform for Distributed Machine Learning on Big Data
Eric P. Xing, Qirong Ho, Wei Dai +7
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 D…