default search action
Sanghamitra Dutta
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j10]Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta:
Robust Algorithmic Recourse Under Model Multiplicity With Probabilistic Guarantees. IEEE J. Sel. Areas Inf. Theory 5: 357-368 (2024) - [j9]Akshaj Kumar Veldanda, Ivan Brugere, Sanghamitra Dutta, Alan Mishler, Siddharth Garg:
Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access. Trans. Mach. Learn. Res. 2024 (2024) - [c20]Faisal Hamman, Sanghamitra Dutta:
Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition. ICLR 2024 - [i28]Shubham Sharma, Sanghamitra Dutta, Emanuele Albini, Freddy Lécué, Daniele Magazzeni, Manuela Veloso:
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values. CoRR abs/2403.08880 (2024) - [i27]Pasan Dissanayake, Sanghamitra Dutta:
Model Reconstruction Using Counterfactual Explanations: Mitigating the Decision Boundary Shift. CoRR abs/2405.05369 (2024) - [i26]Faisal Hamman, Sanghamitra Dutta:
A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition. CoRR abs/2406.04562 (2024) - [i25]Barproda Halder, Faisal Hamman, Pasan Dissanayake, Qiuyi Zhang, Ilia Sucholutsky, Sanghamitra Dutta:
Quantifying Spuriousness of Biased Datasets Using Partial Information Decomposition. CoRR abs/2407.00482 (2024) - [i24]Faisal Hamman, Pasan Dissanayake, Saumitra Mishra, Freddy Lécué, Sanghamitra Dutta:
Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs. CoRR abs/2407.04173 (2024) - 2023
- [j8]Sanghamitra Dutta, Faisal Hamman:
A Review of Partial Information Decomposition in Algorithmic Fairness and Explainability. Entropy 25(5): 795 (2023) - [j7]Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen, Sanghamitra Dutta, Alan Mishler, Siddharth Garg:
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale with MinDiff Loss. Trans. Mach. Learn. Res. 2023 (2023) - [c19]Shubham Sharma, Sanghamitra Dutta, Emanuele Albini, Freddy Lécué, Daniele Magazzeni, Manuela Veloso:
REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values. AIES 2023: 443-453 - [c18]Faisal Hamman, Jiahao Chen, Sanghamitra Dutta:
Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity. FAccT 2023: 1358-1368 - [c17]Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta:
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees. ICML 2023: 12351-12367 - [c16]Sahil Garg, Sanghamitra Dutta, Mina Dalirrooyfard, Anderson Schneider, Yuriy Nevmyvaka:
In- or out-of-distribution detection via dual divergence estimation. UAI 2023: 635-646 - [i23]Akshaj Kumar Veldanda, Ivan Brugere, Sanghamitra Dutta, Alan Mishler, Siddharth Garg:
Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access. CoRR abs/2302.01385 (2023) - [i22]Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta:
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees. CoRR abs/2305.11997 (2023) - [i21]Faisal Hamman, Sanghamitra Dutta:
Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition. CoRR abs/2307.11333 (2023) - 2022
- [b1]Sanghamitra Dutta:
Strategies for Fair, Explainable, and Reliable Machine Learning Using Information Theory. Carnegie Mellon University, USA, 2022 - [c15]Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, Daniele Magazzeni:
Robust Counterfactual Explanations for Tree-Based Ensembles. ICML 2022: 5742-5756 - [c14]Puneet Mathur, Atula Tejaswi Neerkaje, Malika Chhibber, Ramit Sawhney, Fuming Guo, Franck Dernoncourt, Sanghamitra Dutta, Dinesh Manocha:
MONOPOLY: Financial Prediction from MONetary POLicY Conference Videos Using Multimodal Cues. ACM Multimedia 2022: 2276-2285 - [i20]Sanghamitra Dutta, Praveen Venkatesh, Pulkit Grover:
Quantifying Feature Contributions to Overall Disparity Using Information Theory. CoRR abs/2206.08454 (2022) - [i19]Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen, Sanghamitra Dutta, Alan Mishler, Siddharth Garg:
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale. CoRR abs/2206.14853 (2022) - [i18]Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, Daniele Magazzeni:
Robust Counterfactual Explanations for Tree-Based Ensembles. CoRR abs/2207.02739 (2022) - [i17]Faisal Hamman, Jiahao Chen, Sanghamitra Dutta:
Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity. CoRR abs/2211.02139 (2022) - 2021
- [j6]Sanghamitra Dutta, Jianyu Wang, Gauri Joshi:
Slow and Stale Gradients Can Win the Race. IEEE J. Sel. Areas Inf. Theory 2(3): 1012-1024 (2021) - [j5]Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover:
Fairness Under Feature Exemptions: Counterfactual and Observational Measures. IEEE Trans. Inf. Theory 67(10): 6675-6710 (2021) - [c13]Chenyu Jiang, Bowen Wu, Sanghamitra Dutta, Pulkit Grover:
An Information-Theoretic Measure for Enabling Category Exemptions with an Application to Filter Bubbles. BIAS 2021: 117-129 - [c12]Praveen Venkatesh, Sanghamitra Dutta, Neil Mehta, Pulkit Grover:
Can Information Flows Suggest Targets for Interventions in Neural Circuits? NeurIPS 2021: 3149-3162 - [i16]Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha, Di Lu, Joel R. Tetreault, Alex Jaimes:
GTN-ED: Event Detection Using Graph Transformer Networks. CoRR abs/2104.15104 (2021) - [i15]Saumitra Mishra, Sanghamitra Dutta, Jason Long, Daniele Magazzeni:
A Survey on the Robustness of Feature Importance and Counterfactual Explanations. CoRR abs/2111.00358 (2021) - [i14]Praveen Venkatesh, Sanghamitra Dutta, Neil Mehta, Pulkit Grover:
Can Information Flows Suggest Targets for Interventions in Neural Circuits? CoRR abs/2111.05299 (2021) - 2020
- [j4]Sanghamitra Dutta, Haewon Jeong, Yaoqing Yang, Viveck R. Cadambe, Tze Meng Low, Pulkit Grover:
Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing. Proc. IEEE 108(8): 1219-1234 (2020) - [j3]Sanghamitra Dutta, Mohammad Fahim, Farzin Haddadpour, Haewon Jeong, Viveck R. Cadambe, Pulkit Grover:
On the Optimal Recovery Threshold of Coded Matrix Multiplication. IEEE Trans. Inf. Theory 66(1): 278-301 (2020) - [j2]Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover:
Information Flow in Computational Systems. IEEE Trans. Inf. Theory 66(9): 5456-5491 (2020) - [c11]Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover:
An Information-Theoretic Quantification of Discrimination with Exempt Features. AAAI 2020: 3825-3833 - [c10]Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney:
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing. ICML 2020: 2803-2813 - [c9]Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover:
How else can we define Information Flow in Neural Circuits? ISIT 2020: 2879-2884 - [i13]Sanghamitra Dutta, Jianyu Wang, Gauri Joshi:
Slow and Stale Gradients Can Win the Race. CoRR abs/2003.10579 (2020) - [i12]Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover:
Fairness Under Feature Exemptions: Counterfactual and Observational Measures. CoRR abs/2006.07986 (2020)
2010 – 2019
- 2019
- [j1]Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover:
"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products. IEEE Trans. Inf. Theory 65(10): 6171-6193 (2019) - [c8]Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover:
How should we define Information Flow in Neural Circuits? ISIT 2019: 176-180 - [i11]Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover:
Information Flow in Computational Systems. CoRR abs/1902.02292 (2019) - [i10]Sanghamitra Dutta, Ziqian Bai, Tze Meng Low, Pulkit Grover:
CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors. CoRR abs/1903.01042 (2019) - [i9]Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney:
An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy. CoRR abs/1910.07870 (2019) - 2018
- [c7]Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh, Parijat Dube, Priya Nagpurkar:
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD. AISTATS 2018: 803-812 - [c6]Utsav Sheth, Sanghamitra Dutta, Malhar Chaudhari, Haewon Jeong, Yaoqing Yang, Jukka Kohonen, Teemu Roos, Pulkit Grover:
An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation. IEEE BigData 2018: 1113-1120 - [c5]Sanghamitra Dutta, Ziqian Bai, Haewon Jeong, Tze Meng Low, Pulkit Grover:
A Unified Coded Deep Neural Network Training Strategy based on Generalized PolyDot codes. ISIT 2018: 1585-1589 - [i8]Sanghamitra Dutta, Mohammad Fahim, Farzin Haddadpour, Haewon Jeong, Viveck R. Cadambe, Pulkit Grover:
On the Optimal Recovery Threshold of Coded Matrix Multiplication. CoRR abs/1801.10292 (2018) - [i7]Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh, Parijat Dube, Priya Nagpurkar:
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD. CoRR abs/1803.01113 (2018) - [i6]Sanghamitra Dutta, Ziqian Bai, Haewon Jeong, Tze Meng Low, Pulkit Grover:
A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication. CoRR abs/1811.10751 (2018) - [i5]Utsav Sheth, Sanghamitra Dutta, Malhar Chaudhari, Haewon Jeong, Yaoqing Yang, Jukka Kohonen, Teemu Roos, Pulkit Grover:
An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation. CoRR abs/1811.11811 (2018) - 2017
- [c4]Mohammad Fahim, Haewon Jeong, Farzin Haddadpour, Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover:
On the optimal recovery threshold of coded matrix multiplication. Allerton 2017: 1264-1270 - [c3]Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover:
Coded convolution for parallel and distributed computing within a deadline. ISIT 2017: 2403-2407 - [i4]Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover:
"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products. CoRR abs/1704.05181 (2017) - [i3]Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover:
Coded convolution for parallel and distributed computing within a deadline. CoRR abs/1705.03875 (2017) - 2016
- [c2]Sanghamitra Dutta, Pulkit Grover:
Adaptivity provably helps: Information-theoretic limits on l0 cost of non-adaptive sensing. ISIT 2016: 1431-1435 - [c1]Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover:
Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products. NIPS 2016: 2092-2100 - [i2]Sanghamitra Dutta, Pulkit Grover:
Adaptivity provably helps: information-theoretic limits on $l_0$ cost of non-adaptive sensing. CoRR abs/1602.04260 (2016) - 2014
- [i1]Sanghamitra Dutta, Arijit De:
LAMP: A Locally Adapting Matching Pursuit Framework for Group Sparse Signatures in Ultra-Wide Band Radar Imaging. CoRR abs/1411.4020 (2014)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from , , and to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 21:25 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint