activity
20152022
most citedMLlib: Machine Learning in Apache Spark

961 citations · 1.1k across the 10 of their papers we have counts for

collaborators

20 papers

cs.DC20224 cited

Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning

Pengfei Zheng, Rui Pan, Tarannum Khan +2

Dynamic adaptation has become an essential technique in accelerating distributed machine learning (ML) training. Recent studies have shown that dynamically adjusting model structur…

cs.LG202110 cited

KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks

J. Gregory Pauloski, Qi Huang, Lei Huang +4

Kronecker-factored Approximate Curvature (K-FAC) has recently been shown to converge faster in deep neural network (DNN) training than stochastic gradient descent (SGD); however, K…

cs.LG202116 cited

AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning

Yuhan Liu, Saurabh Agarwal, Shivaram Venkataraman

With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data. However, our expe…

cs.DC2021

On the Utility of Gradient Compression in Distributed Training Systems

Saurabh Agarwal, Hongyi Wang, Shivaram Venkataraman +1

A rich body of prior work has highlighted the existence of communication bottlenecks in synchronous data-parallel training. To alleviate these bottlenecks, a long line of recent wo…

cs.LG20217 cited

Accelerating Deep Learning Inference via Learned Caches

Arjun Balasubramanian, Adarsh Kumar, Yuhan Liu +3

Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been…

cs.LG2021

Marius: Learning Massive Graph Embeddings on a Single Machine

Jason Mohoney, Roger Waleffe, Yiheng Xu +2

We propose a new framework for computing the embeddings of large-scale graphs on a single machine. A graph embedding is a fixed length vector representation for each node (and/or e…