Sanghamitra Dutta

78 papers A* 9A 4B 7C 1Journal 51Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures. AAMAS Erfaun Noorani, Pasan Dissanayake, Faisal Hamman, Sanghamitra Dutta
2025	J	`jnl`	Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures. CoRR Erfaun Noorani, Pasan Dissanayake, Faisal Hamman, Sanghamitra Dutta
2025	J	`jnl`	Demystifying the Accuracy-Interpretability Trade-Off: A Case Study of Inferring Ratings from Reviews. CoRR Pranjal Atrey, Michael P. Brundage, Min Wu, Sanghamitra Dutta
2025	J	`jnl`	Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations. CoRR Faisal Hamman, Pasan Dissanayake, Yanjun Fu, Sanghamitra Dutta
2025	J	`jnl`	Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards. CoRR Faisal Hamman, Chenyang Zhu, Anoop Kumar, Xujun Peng, Sanghamitra Dutta, Daben Liu, Alfy Samuel
2025	J	`jnl`	Learning Invariant Graph Representations Through Redundant Information. CoRR Barproda Halder, Pasan Dissanayake, Sanghamitra Dutta
2025	B	`conf`	Private Counterfactual Retrieval with Immutable Features. ISIT Shreya Meel, Pasan Dissanayake, Mohamed W. Nomeir, Sanghamitra Dutta, Sennur Ulukus
2025	A	`conf`	Quantifying Knowledge Distillation using Partial Information Decomposition. AISTATS Pasan Dissanayake, Faisal Hamman, Barproda Halder, Ilia Sucholutsky, Qiuyi Zhang, Sanghamitra Dutta
2025	A*	`conf`	Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs. ICML Faisal Hamman, Pasan Dissanayake, Saumitra Mishra, Freddy Lécué, Sanghamitra Dutta
2025	J	`jnl`	T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning. CoRR Yanjun Fu, Faisal Hamman, Sanghamitra Dutta
2025	J	`jnl`	TabDistill: Distilling Transformers into Neural Nets for Few-Shot Tabular Classification. CoRR Pasan Dissanayake, Sanghamitra Dutta
2025	J	`jnl`	Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition. Trans. Mach. Learn. Res. Barproda Halder, Faisal Hamman, Pasan Dissanayake, Qiuyi Zhang, Ilia Sucholutsky, Sanghamitra Dutta
2025	J	`jnl`	VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation. CoRR David Egea, Barproda Halder, Sanghamitra Dutta
2025	J	`jnl`	What If, But Privately: Private Counterfactual Retrieval. CoRR Shreya Meel, Mohamed W. Nomeir, Pasan Dissanayake, Sanghamitra Dutta, Sennur Ulukus
2024	B	`conf`	A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition. ISIT Faisal Hamman, Sanghamitra Dutta
2024	J	`jnl`	A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition. CoRR Faisal Hamman, Sanghamitra Dutta
2024	A*	`conf`	Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition. ICLR Faisal Hamman, Sanghamitra Dutta
2024	J	`jnl`	Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access. Trans. Mach. Learn. Res. Akshaj Kumar Veldanda, Ivan Brugere, Sanghamitra Dutta, Alan Mishler, Siddharth Garg
2024	A*	`conf`	Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory. NeurIPS Pasan Dissanayake, Sanghamitra Dutta
2024	J	`jnl`	Model Reconstruction Using Counterfactual Explanations: Mitigating the Decision Boundary Shift. CoRR Pasan Dissanayake, Sanghamitra Dutta
2024	J	`jnl`	Private Counterfactual Retrieval With Immutable Features. CoRR Shreya Meel, Pasan Dissanayake, Mohamed W. Nomeir, Sanghamitra Dutta, Sennur Ulukus
2024	J	`jnl`	Private Counterfactual Retrieval. CoRR Mohamed W. Nomeir, Pasan Dissanayake, Shreya Meel, Sanghamitra Dutta, Sennur Ulukus
2024	J	`jnl`	Quantifying Knowledge Distillation Using Partial Information Decomposition. CoRR Pasan Dissanayake, Faisal Hamman, Barproda Halder, Ilia Sucholutsky, Qiuyi Zhang, Sanghamitra Dutta
2024	J	`jnl`	Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs. CoRR Faisal Hamman, Pasan Dissanayake, Saumitra Mishra, Freddy Lécué, Sanghamitra Dutta
2024	J	`jnl`	Quantifying Spuriousness of Biased Datasets Using Partial Information Decomposition. CoRR Barproda Halder, Faisal Hamman, Pasan Dissanayake, Qiuyi Zhang, Ilia Sucholutsky, Sanghamitra Dutta
2024	J	`jnl`	REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values. CoRR Shubham Sharma, Sanghamitra Dutta, Emanuele Albini, Freddy Lécué, Daniele Magazzeni, Manuela Veloso
2024	J	`jnl`	Robust Algorithmic Recourse Under Model Multiplicity With Probabilistic Guarantees. IEEE J. Sel. Areas Inf. Theory Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta
2023	J	`jnl`	A Review of Partial Information Decomposition in Algorithmic Fairness and Explainability. Entropy Sanghamitra Dutta, Faisal Hamman
2023	—	`conf`	Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity. FAccT Faisal Hamman, Jiahao Chen, Sanghamitra Dutta
2023	J	`jnl`	Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition. CoRR Faisal Hamman, Sanghamitra Dutta
2023	J	`jnl`	Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale with MinDiff Loss. Trans. Mach. Learn. Res. Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen, Sanghamitra Dutta, Alan Mishler, Siddharth Garg
2023	J	`jnl`	Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access. CoRR Akshaj Kumar Veldanda, Ivan Brugere, Sanghamitra Dutta, Alan Mishler, Siddharth Garg
2023	A	`conf`	In- or out-of-distribution detection via dual divergence estimation. UAI Sahil Garg, Sanghamitra Dutta, Mina Dalirrooyfard, Anderson Schneider, Yuriy Nevmyvaka
2023	C	`conf`	REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values. AIES Shubham Sharma, Sanghamitra Dutta, Emanuele Albini, Freddy Lécué, Daniele Magazzeni, Manuela Veloso
2023	A*	`conf`	Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees. ICML Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta
2023	J	`jnl`	Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees. CoRR Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta
2022	J	`jnl`	Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity. CoRR Faisal Hamman, Jiahao Chen, Sanghamitra Dutta
2022	J	`jnl`	Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale. CoRR Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen, Sanghamitra Dutta, Alan Mishler, Siddharth Garg
2022	A*	`conf`	MONOPOLY: Financial Prediction from MONetary POLicY Conference Videos Using Multimodal Cues. ACM Multimedia Puneet Mathur, Atula Tejaswi Neerkaje, Malika Chhibber, Ramit Sawhney, Fuming Guo, Franck Dernoncourt, Sanghamitra Dutta, Dinesh Manocha
2022	J	`jnl`	Quantifying Feature Contributions to Overall Disparity Using Information Theory. CoRR Sanghamitra Dutta, Praveen Venkatesh, Pulkit Grover
2022	A*	`conf`	Robust Counterfactual Explanations for Tree-Based Ensembles. ICML Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, Daniele Magazzeni
2022	J	`jnl`	Robust Counterfactual Explanations for Tree-Based Ensembles. CoRR Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, Daniele Magazzeni
2022	—	`—`	Strategies for Fair, Explainable, and Reliable Machine Learning Using Information Theory. Sanghamitra Dutta
2021	J	`jnl`	A Survey on the Robustness of Feature Importance and Counterfactual Explanations. CoRR Saumitra Mishra, Sanghamitra Dutta, Jason Long, Daniele Magazzeni
2021	—	`conf`	An Information-Theoretic Measure for Enabling Category Exemptions with an Application to Filter Bubbles. BIAS Chenyu Jiang, Bowen Wu, Sanghamitra Dutta, Pulkit Grover
2021	A*	`conf`	Can Information Flows Suggest Targets for Interventions in Neural Circuits? NeurIPS Praveen Venkatesh, Sanghamitra Dutta, Neil Ashim Mehta, Pulkit Grover
2021	J	`jnl`	Can Information Flows Suggest Targets for Interventions in Neural Circuits? CoRR Praveen Venkatesh, Sanghamitra Dutta, Neil Ashim Mehta, Pulkit Grover
2021	J	`jnl`	Fairness Under Feature Exemptions: Counterfactual and Observational Measures. IEEE Trans. Inf. Theory Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover
2021	J	`jnl`	GTN-ED: Event Detection Using Graph Transformer Networks. CoRR Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha, Di Lu, Joel R. Tetreault, Alex Jaimes
2021	J	`jnl`	Slow and Stale Gradients Can Win the Race. IEEE J. Sel. Areas Inf. Theory Sanghamitra Dutta, Jianyu Wang, Gauri Joshi
2020	J	`jnl`	Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing. Proc. IEEE Sanghamitra Dutta, Haewon Jeong, Yaoqing Yang, Viveck R. Cadambe, Tze Meng Low, Pulkit Grover
2020	A*	`conf`	An Information-Theoretic Quantification of Discrimination with Exempt Features. AAAI Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover
2020	J	`jnl`	Fairness Under Feature Exemptions: Counterfactual and Observational Measures. CoRR Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover
2020	B	`conf`	How else can we define Information Flow in Neural Circuits? ISIT Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover
2020	J	`jnl`	Information Flow in Computational Systems. IEEE Trans. Inf. Theory Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover
2020	A*	`conf`	Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing. ICML Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney
2020	J	`jnl`	On the Optimal Recovery Threshold of Coded Matrix Multiplication. IEEE Trans. Inf. Theory Sanghamitra Dutta, Mohammad Fahim, Farzin Haddadpour, Haewon Jeong, Viveck R. Cadambe, Pulkit Grover
2020	J	`jnl`	Slow and Stale Gradients Can Win the Race. CoRR Sanghamitra Dutta, Jianyu Wang, Gauri Joshi
2019	J	`jnl`	"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products. IEEE Trans. Inf. Theory Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover
2019	J	`jnl`	An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy. CoRR Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney
2019	J	`jnl`	CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors. CoRR Sanghamitra Dutta, Ziqian Bai, Tze Meng Low, Pulkit Grover
2019	B	`conf`	How should we define Information Flow in Neural Circuits? ISIT Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover
2019	J	`jnl`	Information Flow in Computational Systems. CoRR Praveen Venkatesh, Sanghamitra Dutta, Pulkit Grover
2018	J	`jnl`	A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication. CoRR Sanghamitra Dutta, Ziqian Bai, Haewon Jeong, Tze Meng Low, Pulkit Grover
2018	B	`conf`	A Unified Coded Deep Neural Network Training Strategy based on Generalized PolyDot codes. ISIT Sanghamitra Dutta, Ziqian Bai, Haewon Jeong, Tze Meng Low, Pulkit Grover
2018	—	`conf`	An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation. IEEE BigData Utsav Sheth, Sanghamitra Dutta, Malhar Chaudhari, Haewon Jeong, Yaoqing Yang, Jukka Kohonen, Teemu Roos, Pulkit Grover
2018	J	`jnl`	An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation. CoRR Utsav Sheth, Sanghamitra Dutta, Malhar Chaudhari, Haewon Jeong, Yaoqing Yang, Jukka Kohonen, Teemu Roos, Pulkit Grover
2018	J	`jnl`	On the Optimal Recovery Threshold of Coded Matrix Multiplication. CoRR Sanghamitra Dutta, Mohammad Fahim, Farzin Haddadpour, Haewon Jeong, Viveck R. Cadambe, Pulkit Grover
2018	A	`conf`	Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD. AISTATS Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh, Parijat Dube, Priya Nagpurkar
2018	J	`jnl`	Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD. CoRR Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh, Parijat Dube, Priya Nagpurkar
2017	J	`jnl`	"Short-Dot": Computing Large Linear Transforms Distributedly Using Coded Short Dot Products. CoRR Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover
2017	B	`conf`	Coded convolution for parallel and distributed computing within a deadline. ISIT Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover
2017	J	`jnl`	Coded convolution for parallel and distributed computing within a deadline. CoRR Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover
2017	—	`conf`	On the optimal recovery threshold of coded matrix multiplication. Allerton Mohammad Fahim, Haewon Jeong, Farzin Haddadpour, Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover
2016	B	`conf`	Adaptivity provably helps: Information-theoretic limits on l0 cost of non-adaptive sensing. ISIT Sanghamitra Dutta, Pulkit Grover
2016	J	`jnl`	Adaptivity provably helps: information-theoretic limits on $l_0$ cost of non-adaptive sensing. CoRR Sanghamitra Dutta, Pulkit Grover
2016	—	`conf`	Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products. NIPS Sanghamitra Dutta, Viveck R. Cadambe, Pulkit Grover
2014	J	`jnl`	LAMP: A Locally Adapting Matching Pursuit Framework for Group Sparse Signatures in Ultra-Wide Band Radar Imaging. CoRR Sanghamitra Dutta, Arijit De