Sanghamitra Dutta
13 papers · 2016–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Conference Polyglot (7) π Academic Marathon (9) π§ Keyword Pioneer π Interdisciplinary Bridge π Cross-Pollinator (6)
π
Cross-Pollinator
(6)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(27)
π
Keyword Champion
(2)
π
Grand Slam
π₯
Unstoppable
(6)
ποΈ
Keyword Collector
(54)
π
Trend Setter
π
Century Club
(13)
β
The Questioner
(2)
Conferences
ICML (4)
NIPS (3)
AISTATS (2)
AAAI (1)
ICLR (1)
NAACL (1)
UAI (1)
Top co-authors
Keywords
counterfactual explanation
(3)
information theory
(2)
neural network
(2)
straggler mitigation
(2)
algorithmic fairness
(1)
domain adaptation
(1)
neural network pruning
(1)
distributed learning
(1)
stochastic gradient descent
(1)
distributed computing
(1)
hypothesis testing
(1)
kullback-leibler divergence
(1)
event detection
(1)
tree-based ensemble
(1)
asynchronous training
(1)
dependency parsing
(1)
chernoff bound
(1)
decision boundary
(1)
surrogate model
(1)
model robustness
(1)
Papers
Quantifying Knowledge Distillation using Partial Information Decomposition
AISTATS 2025
Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs
ICML 2025
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
NIPS 2024
Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
ICLR 2024
In- or out-of-distribution detection via dual divergence estimation
UAI 2023
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
ICML 2023
Robust Counterfactual Explanations for Tree-Based Ensembles
ICML 2022
Can Information Flows Suggest Targets for Interventions in Neural Circuits?
NIPS 2021
GTN-ED: Event Detection Using Graph Transformer Networks
NAACL 2021
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
ICML 2020
An Information-Theoretic Quantification of Discrimination with Exempt Features
AAAI 2020
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD
AISTATS 2018
Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products
NIPS 2016