Sanghamitra Dutta

Orcid: 0000-0002-6500-2627

According to our database1, Sanghamitra Dutta authored at least 38 papers between 2014 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale with MinDiff Loss.
Trans. Mach. Learn. Res., 2023

A Review of Partial Information Decomposition in Algorithmic Fairness and Explainability.
Entropy, 2023

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition.
CoRR, 2023

Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access.
CoRR, 2023

In- or out-of-distribution detection via dual divergence estimation.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees.
Proceedings of the International Conference on Machine Learning, 2023

Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity.
Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, 2023

REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values.
Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023

2022
Strategies for Fair, Explainable, and Reliable Machine Learning Using Information Theory.
PhD thesis, 2022

Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity.
CoRR, 2022

Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale.
CoRR, 2022

Quantifying Feature Contributions to Overall Disparity Using Information Theory.
CoRR, 2022

MONOPOLY: Financial Prediction from MONetary POLicY Conference Videos Using Multimodal Cues.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Robust Counterfactual Explanations for Tree-Based Ensembles.
Proceedings of the International Conference on Machine Learning, 2022

2021
Fairness Under Feature Exemptions: Counterfactual and Observational Measures.
IEEE Trans. Inf. Theory, 2021

Slow and Stale Gradients Can Win the Race.
IEEE J. Sel. Areas Inf. Theory, 2021

A Survey on the Robustness of Feature Importance and Counterfactual Explanations.
CoRR, 2021

GTN-ED: Event Detection Using Graph Transformer Networks.
CoRR, 2021

Can Information Flows Suggest Targets for Interventions in Neural Circuits?
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

An Information-Theoretic Measure for Enabling Category Exemptions with an Application to Filter Bubbles.
Proceedings of the Advances in Bias and Fairness in Information Retrieval, 2021

2020
Information Flow in Computational Systems.
IEEE Trans. Inf. Theory, 2020

On the Optimal Recovery Threshold of Coded Matrix Multiplication.
IEEE Trans. Inf. Theory, 2020

Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing.
Proc. IEEE, 2020

How else can we define Information Flow in Neural Circuits?
Proceedings of the IEEE International Symposium on Information Theory, 2020

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing.
Proceedings of the 37th International Conference on Machine Learning, 2020

An Information-Theoretic Quantification of Discrimination with Exempt Features.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products.
IEEE Trans. Inf. Theory, 2019

An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy.
CoRR, 2019

CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors.
CoRR, 2019

How should we define Information Flow in Neural Circuits?
Proceedings of the IEEE International Symposium on Information Theory, 2019

2018
A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication.
CoRR, 2018

A Unified Coded Deep Neural Network Training Strategy based on Generalized PolyDot codes.
Proceedings of the 2018 IEEE International Symposium on Information Theory, 2018

An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation.
Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2018), 2018

Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017
Coded convolution for parallel and distributed computing within a deadline.
Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

2016
Adaptivity provably helps: information-theoretic limits on $l_0$ cost of non-adaptive sensing.
CoRR, 2016

Adaptivity provably helps: Information-theoretic limits on l0 cost of non-adaptive sensing.
Proceedings of the IEEE International Symposium on Information Theory, 2016

2014
LAMP: A Locally Adapting Matching Pursuit Framework for Group Sparse Signatures in Ultra-Wide Band Radar Imaging.
CoRR, 2014


  Loading...