activity
20172021
most citedCodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors

4 citations · 4 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CL2021

GTN-ED: Event Detection Using Graph Transformer Networks

Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha +3

Recent works show that the graph structure of sentences, generated from dependency parsers, has potential for improving event detection. However, they often only leverage the edges…

stat.ML2020

Slow and Stale Gradients Can Win the Race

Sanghamitra Dutta, Jianyu Wang, Gauri Joshi

Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in runtime as it waits for the slowest workers (stragglers). Asynchronous method…

stat.ML2019

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing

Sanghamitra Dutta, Dennis Wei, Hazar Yueksel +3

A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should dec…

cs.IT20194 cited

CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors

Sanghamitra Dutta, Ziqian Bai, Tze Meng Low +1

This work proposes the first strategy to make distributed training of neural networks resilient to computing errors, a problem that has remained unsolved despite being first posed…

cs.IT2018

An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation

Utsav Sheth, Sanghamitra Dutta, Malhar Chaudhari +5

We propose a novel application of coded computing to the problem of the nearest neighbor estimation using MatDot Codes [Fahim. et.al. 2017], that are known to be optimal for matrix…

cs.IT2018

A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication

Sanghamitra Dutta, Ziqian Bai, Haewon Jeong +2

This paper has two contributions. First, we propose a novel coded matrix multiplication technique called Generalized PolyDot codes that advances on existing methods for coded matri…