87 citations · 222 across the 32 of their papers we have counts for
13 papers · 1 filter
What If, But Privately: Private Counterfactual Retrieval
Shreya Meel, Mohamed Nomeir, Pasan Dissanayake +2
Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual exp…
Private Counterfactual Retrieval With Immutable Features
Shreya Meel, Pasan Dissanayake, Mohamed Nomeir +2
In a classification task, counterfactual explanations provide the minimum change needed for an input to be classified into a favorable class. We consider the problem of privately r…
Private Counterfactual Retrieval
Mohamed Nomeir, Pasan Dissanayake, Shreya Meel +2
Transparency and explainability are two extremely important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterf…
A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition
Faisal Hamman, Sanghamitra Dutta
This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equaliz…
Can Information Flows Suggest Targets for Interventions in Neural Circuits?
Praveen Venkatesh, Sanghamitra Dutta, Neil Mehta +1
Motivated by neuroscientific and clinical applications, we empirically examine whether observational measures of information flow can suggest interventions. We do so by performing…
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…
Information Flow in Computational Systems
Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover
We develop a theoretical framework for defining and identifying flows of information in computational systems. Here, a computational system is assumed to be a directed graph, with…
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…
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…
Coded convolution for parallel and distributed computing within a deadline
Sanghamitra Dutta, Viveck Cadambe, Pulkit Grover
We consider the problem of computing the convolution of two long vectors using parallel processing units in the presence of "stragglers". Stragglers refer to the small fraction of…
"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products
Sanghamitra Dutta, Viveck Cadambe, Pulkit Grover
Faced with saturation of Moore's law and increasing dimension of data, system designers have increasingly resorted to parallel and distributed computing. However, distributed compu…
Adaptivity provably helps: information-theoretic limits on cost of non-adaptive sensing
Sanghamitra Dutta, Pulkit Grover
The advantages of adaptivity and feedback are of immense interest in signal processing and communication with many positive and negative results. Although it is established that ad…
LAMP: A Locally Adapting Matching Pursuit Framework for Group Sparse Signatures in Ultra-Wide Band Radar Imaging
Sanghamitra Dutta, Arijit De
It has been found that radar returns of extended targets are not only sparse but also exhibit a tendency to cluster into randomly located, variable sized groups. However, the stand…