publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. arXiv
    Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
    Nyal Patel, Matthieu Bou, Arjun Jagota, and 2 more authors
    arXiv preprint arXiv:2510.06092, 2025
  2. arXiv
    The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
    Matthieu Bou, Nyal Patel, Arjun Jagota, and 2 more authors
    arXiv preprint arXiv:2510.06096, 2025
  3. MLHC
    Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
    Anish Narain, Ritam Majumdar, Nikita Narayanan, and 2 more authors
    In Proceedings of Machine Learning Research, 2025
  4. Anaesthesia
    Surgical precision? Cutting through the hype of AI-augmented peri-operative risk prediction
    M Murali, J Mann, and Sonali Parbhoo
    Anaesthesia, 2025
  5. AMIA
    Where do doctors disagree? Characterizing Decision Points for Safe Reinforcement Learning in Choosing Vasopressor Treatment
    E Brown, S Raval, A Rojas, and 6 more authors
    In AMIA Annual Symposium Proceedings, 2025
  6. arXiv
    Causal Bayesian Optimization with Unknown Graphs
    Jean Durand, Yashas Annadani, Stefan Bauer, and 1 more author
    arXiv preprint arXiv:2503.19554, 2025
  7. COLM
    Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
    J Joselowitz, R Majumdar, A Jagota, and 4 more authors
    In Conference on Language Modeling, 2025
  8. RLC
    Concept-Based Off-Policy Evaluation
    Ritam Majumdar, J Teversham, and Sonali Parbhoo
    In Reinforcement Learning Conference, 2025
  9. IUI
    User Studies in Human-Feature-Integration
    Yixin Li, Lucas Lefebvre, Sonali Parbhoo, and 2 more authors
    In Joint Proceedings of the ACM IUI Workshops, 2025
  10. ICLR Workshop
    AlphaGo or beta-hCG: a reinforcement learning framework for assisted conception
    S Hanassab, E Sheremetyeva, Sonali Parbhoo, and 3 more authors
    In ICLR Workshop on AI for Children: Healthcare, Psychology, Education, 2025
  11. AISTATS
    Do regularization methods for shortcut mitigation work as intended?
    Haoyang Hong, Ioanna Papanikolaou, and Sonali Parbhoo
    In The 28th International Conference on Artificial Intelligence and Statistics, 2025
  12. AISTATS
    Decision-point guided safe policy improvement
    Abhishek Sharma, Leo Benac, Sonali Parbhoo, and 1 more author
    In The 28th International Conference on Artificial Intelligence and Statistics, 2025

2024

  1. arXiv
    Inverse Transition Learning: Learning Dynamics from Demonstrations
    L Benac, A Sharma, Sonali Parbhoo, and 1 more author
    arXiv preprint arXiv:2411.05174, 2024
  2. arXiv
    Tree-based leakage inspection and control in concept bottleneck models
    Angelos Ragkousis and Sonali Parbhoo
    arXiv preprint arXiv:2410.06352, 2024
  3. Blood
    CD8+ T-cell differentiation and dysfunction inform treatment response in acute myeloid leukemia
    F Mazziotta, L Biavati, J Rimando, and 4 more authors
    Blood, 2024
  4. arXiv
    Towards Integrating Personal Knowledge into Test-Time Predictions
    Isaac Lage, Sonali Parbhoo, and Finale Doshi-Velez
    arXiv preprint arXiv:2406.08636, 2024
  5. arXiv
    Guarantee Regions for Local Explanations
    Marton Havasi, Sonali Parbhoo, and Finale Doshi-Velez
    arXiv preprint arXiv:2402.12737, 2024
  6. JMLR
    Rethinking discount regularization: New interpretations, unintended consequences, and solutions for regularization in reinforcement learning
    Sarah Rathnam, Sonali Parbhoo, Siddharth Swaroop, and 3 more authors
    Journal of Machine Learning Research, 2024
  7. TMLR
    Task-Relevant Feature Selection with Prediction Focused Mixture Models
    Abhishek Sharma, Catherine Zeng, Sanjana Narayanan, and 3 more authors
    Transactions on Machine Learning Research, 2024
  8. MLHC
    Decision-Focused Model-based Reinforcement Learning for Reward Transfer
    Abhishek Sharma, Sonali Parbhoo, Omer Gottesman, and 1 more author
    In Proceedings of Machine Learning Research, 2024

2023

  1. arXiv
    Bayesian Inverse Transition Learning for Offline Settings
    L Benac, Sonali Parbhoo, and Finale Doshi-Velez
    arXiv preprint arXiv:2308.05075, 2023
  2. ICML Workshop
    Leveraging factored action spaces for off-policy evaluation
    A Rebello, S Tang, J Wiens, and 1 more author
    In ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023
  3. ICML
    The unintended consequences of discount regularization: Improving regularization in certainty equivalence reinforcement learning
    S Rathnam, Sonali Parbhoo, W Pan, and 2 more authors
    In International Conference on Machine Learning, 2023
  4. ATS
    Early Vs Late Initiation of Vasopressors in Sepsis: An Augmented Inverse Probability Weighting Approach
    DC Marshall, J Zhang, S Hao, and 3 more authors
    In American Thoracic Society 2023 International Conference, 2023
  5. TMLR
    Risk sensitive dead-end identification in safety-critical offline reinforcement learning
    TW Killian, Sonali Parbhoo, and M Ghassemi
    Transactions on Machine Learning Research, 2023
  6. CAMLIS
    Adaptive experimental design for intrusion data collection
    K Highnam, Z Hanif, E Van Vogt, and 3 more authors
    In CAMLIS’23: Conference on Applied Machine Learning for Information Security, 2023

2022

  1. MLHC
    Learning optimal summaries of clinical time-series with concept bottleneck models
    C Wu, Sonali Parbhoo, M Havasi, and 1 more author
    In Machine Learning for Healthcare Conference, 2022
  2. NeurIPS
    Addressing leakage in concept bottleneck models
    Marton Havasi, Sonali Parbhoo, and Finale Doshi-Velez
    In Advances in Neural Information Processing Systems, 2022
  3. arXiv
    Policy optimization with sparse global contrastive explanations
    J Yao, Sonali Parbhoo, W Pan, and 1 more author
    arXiv preprint arXiv:2207.06269, 2022
  4. BMJ HCI
    Operationalising fairness in medical algorithms
    Sonali Parbhoo, JW Gichoya, LA Celi, and 1 more author
    BMJ Health & Care Informatics, 2022
  5. AMIA
    Learning predictive and interpretable timeseries summaries from ICU data
    N Johnson, Sonali Parbhoo, AS Ross, and 1 more author
    In AMIA Annual Symposium Proceedings, 2022
  6. arXiv
    Generalizing off-policy evaluation from a causal perspective for sequential decision-making
    Sonali Parbhoo, S Joshi, and Finale Doshi-Velez
    arXiv preprint arXiv:2201.08262, 2022
  7. DAGM GCPR
    Learning Conditional Invariance Through Cycle Consistency
    Sonali Parbhoo and Volker Roth
    In Pattern Recognition: 43rd DAGM German Conference, 2022

2021

  1. DAGM GCPR
    Learning conditional invariance through cycle consistency
    M Samarin, V Nesterov, M Wieser, and 3 more authors
    2021
  2. JAIR
    Optimizing for interpretability in deep neural networks with tree regularization
    Mike Wu, Sonali Parbhoo, MC Hughes, and 2 more authors
    Journal of Artificial Intelligence Research, 2021
  3. TMLR
    Learning-to-defer for sequential medical decision-making under uncertainty
    S Joshi, Sonali Parbhoo, and Finale Doshi-Velez
    Transactions on Machine Learning Research, 2021
  4. AMIA
    Preferential mixture-of-experts: Interpretable models that rely on human expertise as much as possible
    MF Pradier, J Zazo, Sonali Parbhoo, and 3 more authors
    In AMIA Summits on Translational Science Proceedings, 2021
  5. arXiv
    Ncore: Neural counterfactual representation learning for combinations of treatments
    Sonali Parbhoo, Stefan Bauer, and Patrick Schwab
    arXiv preprint arXiv:2103.11175, 2021
  6. Nat Commun
    Real-time prediction of COVID-19 related mortality using electronic health records
    P Schwab, A Mehrjou, Sonali Parbhoo, and 5 more authors
    Nature Communications, 2021

2020

  1. JAIDS
    Host genomics of the HIV-1 reservoir size and its decay rate during suppressive antiretroviral treatment
    CW Thorball, A Borghesi, N Bachmann, and 3 more authors
    JAIDS Journal of Acquired Immune Deficiency Syndromes, 2020
  2. ICML
    Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions
    Omer Gottesman, J Futoma, Y Liu, and 4 more authors
    In International Conference on Machine Learning, 2020
  3. MLHC
    Transfer Learning from Well-Curated to Less-Resourced Populations with HIV
    Sonali Parbhoo, Mario Wieser, Volker Roth, and 1 more author
    In Proceedings of Machine Learning Research, 2020
  4. Entropy
    Information bottleneck for estimating treatment effects with systematically missing covariates
    Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, and 1 more author
    Entropy, 2020
  5. NeurIPS
    Inverse Learning of Symmetries
    Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek, and 1 more author
    In Advances in Neural Information Processing Systems, 2020

2019

  1. PhD Thesis
    Causal Inference and Interpretable Machine Learning for Personalised Medicine
    Sonali Parbhoo
    University of Basel, 2019
  2. Nat Commun
    Determinants of HIV-1 reservoir size and long-term dynamics during suppressive ART
    N Bachmann, C Von Siebenthal, V Vongrad, and 3 more authors
    Nature Communications, 2019
  3. CVPR
    Greedy structure learning of hierarchical compositional models
    A Kortylewski, A Wieczorek, M Wieser, and 3 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019

2018

  1. PLOS ONE
    Improving counterfactual reasoning with kernelised dynamic mixing models
    Sonali Parbhoo, Omer Gottesman, AS Ross, and 4 more authors
    PloS One, 2018

2017

  1. AAAI
    Beyond sparsity: Tree regularization of deep models for interpretability
    Mike Wu, MC Hughes, Sonali Parbhoo, and 3 more authors
    In 32nd AAAI Conference on Artificial Intelligence, 2017
  2. AMIA
    Combining kernel and model based learning for HIV therapy selection
    Sonali Parbhoo, J Bogojeska, M Zazzi, and 2 more authors
    In AMIA Summits on Translational Science Proceedings, 2017

2016

  1. AISTATS
    Bayesian markov blanket estimation
    D Kaufmann, Sonali Parbhoo, A Wieczorek, and 3 more authors
    In Artificial Intelligence and Statistics, 2016

2014

  1. MSc Thesis
    A reinforcement learning design for HIV clinical trials
    Sonali Parbhoo
    University of the Witwatersrand, 2014