Research Papers
All authors were affiliated with J.P. Morgan AI Research at the time of publication, unless otherwise specified.
Interpreting Language Reward Models via Contrastive Explanations
Junqi Jiang, Tom Bewley, Saumitra Mishra, Freddy Lecue, Manuela Veloso
International Conference on Learning Representations (ICLR), January 2025
PICE: Counterfactuals on the Decision Boundary for Piecewise Linear Networks
Mattia Villani, Emanuele Albini, Shubham Sharma, Salim Amoukou, Saumitra Mishra, Daniele Magazzeni, Manuela Veloso
AAAI Conference on AI, Ethics, and Society (AIES), October 2024
Sequential Harmful Shift Detection Without Labels
Salim I Amoukou, Tom Bewley, Saumitra Mishra, Freddy Lecue, Daniele Magazzeni, Manuela Veloso
Conference on Neural Information Processing Systems (NeurIPS), September 2024
Are Logistic Models Really Interpretable?
Danial Dervovic, Freddy Lecue, Nicolas Marchesotti, Daniele Magazzeni
International Joint Conference on Artificial Intelligence (IJCAI), August 2024
Progressive Inference: Explaining Decoder-Only Sequence Classification Models using Intermediate Predictions
Sanjay Kariyappa, Freddy Lecue, Saumitra Mishra, Christopher Pond, Daniele Magazzeni, Manuela Veloso
International Conference on Machine Learning (ICML), July 2024
Counterfactual Metarules for Local and Global Recourse
Tom Bewley, Salim Amoukou, Saumitra Mishra, Daniele Magazzeni, Manuela Veloso
International Conference on Machine Learning (ICML), July 2024
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
Yvonne Zhou, Mingyu Liang, Ivan Brugere, Dana Dachman-Soled, Danial Dervovic, Antigoni Polychroniadou, Min Wu
International Conference on Machine Learning (ICML), July 2024
Robust Algorithmic Recourse Under Model Multiplicity With Probabilistic Guarantees
Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta
IEEE Journal on Selected Areas in Information Theory, Special Issue: Information-Theoretic Methods for Trustworthy and Reliable Machine Learning, May 2024
SHAP@k: Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
Sanjay Kariyappa, Leonidas Tsepenekas, Freddy Lecue, Daniele Magazzeni
AAAI Conference on Artificial Intelligence (AAAI), February 2024
SafeAR: Towards Safer Algorithmic Recourse by Risk-Aware Policies
Haochen Wu, Shubham Sharma, Sunandita Patra, and Sriram Gopalakrishnan
AAAI Conference on Artificial Intelligence (AAAI), February 2024
Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions
Leonidas Tsepenekas, Ivan Brugere, Freddy Lecue, Daniele Magazzeni
Conference on Neural Information Processing Systems (NeurIPS), September 2023
REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values
Shubham Sharma, Sanghamitra Dutta, Emanuele Albini, Freddy Lecue, Daniele Magazzeni, Manuela Veloso
AAAI/ACM Conference on AI Ethics and Society (AIES), May 2023
On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
Emanuele Albini, Shubham Sharma, Saumitra Mishra, Danial Dervovic, Daniele Magazzeni
AAAI/ACM Conference on AI Ethics and Society (AIES), May 2023
GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations
Dan Ley, Saumitra Mishra, Daniele Magazzeni
International Conference on Machine Learning (ICML), April 2023
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
Faisal Hamman (external), Erfaun Noorani (external), Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta (external)
International Conference on Machine Learning (ICML), April 2023
Bayesian Hierarchical Models for Counterfactual Estimation
Natraj Raman, Daniele Magazzeni, Sameena Shah
International Conference on Artificial Intelligence and Statistics (AISTATS), January 2023
CLEAR: Generative Counterfactual Explanations on Graphs
Jing Ma (external), Ruocheng Guo (external), Saumitra Mishra, Aidong Zhang (external), Jundong Li (external)
Neural Information Processing Systems (NeurIPS’22), December 2022
Robust Counterfactual Explanations for Tree-Based Ensembles | Poster| Slides
Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, Daniele Magazzeni
International Conference on Machine Learning (ICML’22), July 2022
Explaining Preference-driven Schedules: the EXPRES Framework
Alberto Pozanco, Francesca Mosca, Parisa Zehtabi, Daniele Magazzeni, Sarit Kraus
ICAPS'22, June 2022
Towards Learning to Explain with Concept Bottleneck Models: Mitigating Information Leakage
Joshua Lockhart, Nicolas Marchesotti, Daniele Magazzeni, Manuela Veloso
ICLR'22 Workshop on Socially Responsible Machine Learning, April 2022
Global Counterfactual Explanations: Investigations, Implementations and Improvements
Dan Ley, Saumitra Mishra, Daniele Magazzeni
ICLR'22 Workshop on Privacy Accountability, Interpretability, Robustness, Reasoning on Structured Data, March 2022
Counterfactual Shapley Additive Explanations
Emanuele Albini, Jason Long, Danial Dervovic, Daniele Magazzeni
ACM Conference on Fairness, Accountability, and Transparency (FAccT'22), January 2022
A Survey on the Robustness of Feature Importance and Counterfactual Explanations
Saumitra Mishra, Sanghamitra Dutta, Jason Long, Daniele Magazzeni
ICAIF’21 Workshop on Explainable AI in Finance, November 2021
Counterfactual Explanations for Arbitrary Regression Models
Thomas Spooner, Danial Dervovic, Jason Long, Jon Shepard, Jiahao Chen, Daniele Magazzeni
ICML’21 Workshop on Algorithmic Recourse, July 2021