Hi, I'm Sonali, an Assistant Professor at Imperial College London.
Hi, I'm Sonali, an Assistant Professor at Imperial College London.
Embedded Files
Sonali is an Assistant Professor and leader of the AI for Actionable Impact (AI4AI) lab at Imperial College London. Her research focuses on sequential decision-making in uncertainty, causal inference and building interpretable models to improve clinical care and deepen our understanding of human health, with applications in areas such as HIV and critical care.
Sonali is an Assistant Professor and leader of the AI for Actionable Impact (AI4AI) lab at Imperial College London. Her research focuses on sequential decision-making in uncertainty, causal inference and building interpretable models to improve clinical care and deepen our understanding of human health, with applications in areas such as HIV and critical care.
She was recently named a Rising Star in AI in 2021. Her work has been published at a number of machine learning conferences such as NeurIPS, AAAI, ICML and AISTATS as well as journals such as Nature Medicine, Nature Communications, AMIA, PLOS and JAIDS. Prior to joining Imperial College, Sonali was a postdoctoral research fellow at Harvard and a Swiss National Science Fellow. Sonali received her PhD (summa cum laude) in 2019 from the University of Basel, Switzerland where she built intelligent models for understanding the interplay between host and virus in the fight against HIV.
She was recently named a Rising Star in AI in 2021. Her work has been published at a number of machine learning conferences such as NeurIPS, AAAI, ICML and AISTATS as well as journals such as Nature Medicine, Nature Communications, AMIA, PLOS and JAIDS. Prior to joining Imperial College, Sonali was a postdoctoral research fellow at Harvard and a Swiss National Science Fellow. Sonali received her PhD (summa cum laude) in 2019 from the University of Basel, Switzerland where she built intelligent models for understanding the interplay between host and virus in the fight against HIV.
Apart from her research, Sonali is passionate about encouraging more discussion on the role of ethics in developing machine learning technologies to actively improve society.
Apart from her research, Sonali is passionate about encouraging more discussion on the role of ethics in developing machine learning technologies to actively improve society.
Imperial College London, South Kensington Campus, SW7 2AZ
I am currently actively looking for PhD students interested in working on reinforcement learning, causal inference, bayesian methods and interpretability for healthcare. Please send me an email if you are interested in applying.
Preprints
Preprints
Note that this list of publications is not up to date. Please refer to my google scholar page and my cv for the most up to date list of publications.
Transfer Learning from Well-Curated to Less-Resourced Populations with HIV.
Transfer Learning from Well-Curated to Less-Resourced Populations with HIV.
Sonali Parbhoo, Mario Wieser, Volker Roth, Finale Doshi-Velez, arXiv pre-print 2020.
Interpretable Off-Policy Evaluation by Highlighting Influential Transitions.
Interpretable Off-Policy Evaluation by Highlighting Influential Transitions.
Omer Gottesman, Joseph Futoma, Yao Liu, Sonali Parbhoo, Leo Celi, Emma Brunskill, Finale Doshi-Velez, arXiv pre-print 2020.
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization.
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization.
Mike Wu, Sonali Parbhoo, Michael Hughes, Volker Roth, Finale Doshi-Velez, arXiv pre-print 2020.
Inverse Learning of Symmetry Transformations.
Inverse Learning of Symmetry Transformations.
Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek, Volker Roth, arXiv pre-print 2020.
Intelligent Policy Mixing for Improved HIV-1 Therapy Selection.
Intelligent Policy Mixing for Improved HIV-1 Therapy Selection.
Sonali Parbhoo, Jasmina Bogojeska, Mario Wieser, Fabricio Arend Torres, Maurizio Zazzi, Susana Posada Cespedes, Niko Beerenwinkel, Enos Bernasconi, Manuel Battegay, Alexander Calmy, Matthias Cavassini, Pietro Vernazza, Andri Rauch, Karin Metzner, Roger Kouyos, Huldrych F. Guenthard, Finale Doshi-Velez, Volker Roth, pre-print 2020.
Host genomics of the HIV-1 reservoir size and its decay rate during suppressive antiretroviral treatment.
Host genomics of the HIV-1 reservoir size and its decay rate during suppressive antiretroviral treatment.
Christian W. Thorball, Alessandro Borghesi, Nadine Bachmann, Chantal von Siebenthal, Valentina Vongrad, Teja Turk, Kathrin Neumann, Niko Beerenwinkel, Jasmina Bogojeska, Volker Roth, Yik Lim Kok, Sonali Parbhoo, Mario Wieser, Jurg Boni, Matthieu Perreau, Thomas Klimkait, Sabine Yerly, Manuel Battegay, Andri Rauch, Patrick Schmid, Enos Bernasconi, Matthias Cavassini, Roger D. Kouyos, Huldrych F. Guenthard, Karin J. Metzner, Jacques Fellay and the Swiss HIV Cohort Study, medRxiv pre-print 2020.
Publications
Publications
Information Bottleneck for Estimating Treatment Effects with Systematically Missing Covariates.
Information Bottleneck for Estimating Treatment Effects with Systematically Missing Covariates.
Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, Volker Roth. Entropy 2020, 22(4), 389;
Greedy Structure Learning of Hierarchical Compositional Models.
Greedy Structure Learning of Hierarchical Compositional Models.
Adam Kortylewski, Aleksander Wieczorek, Mario Wieser, Clemens Blumer, Andreas Morel-Forster, Sonali Parbhoo, Volker Roth, Thomas Vetter. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019.
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability.
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability.
Mike Wu, Michael Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez. In Proceedings AAAI 2018.
Regional Tree Regularization for Interpretability in Black Box Models.
Regional Tree Regularization for Interpretability in Black Box Models.
Mike Wu, Sonali Parbhoo, Michael Hughes, Ryan Kindle, Leo Celi, Volker Roth, Finale Doshi-Velez. In Proceedings AAAI 2020, Contributed Talk.
Improving Counterfactual Reasoning with Kernelised Dynamic Mixing Models.
Improving Counterfactual Reasoning with Kernelised Dynamic Mixing Models.
Sonali Parbhoo, Omer Gottesman, Andrew Slavin Ross, Matthieu Komorowski, Aldo Faisal, Isabella Bon, Volker Roth, Finale Doshi-Velez. PLoS One 2018, 13(11).
Combining Kernel and Model-Based Learning for HIV Therapy Selection.
Combining Kernel and Model-Based Learning for HIV Therapy Selection.
Sonali Parbhoo, Jasmina Bogojeska, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez. In Proceedings of AMIA Joint Summit on Translational Science, 2017, pp 239 - 248.
Determinants of HIV-1 Reservoir Size and Long-Term Dynamics.
Determinants of HIV-1 Reservoir Size and Long-Term Dynamics.
Nadine Bachmann, Chantal von Siebenthal, Valentina Vongrad, Teja Turk, Kathrin Neumann, Niko Beerenwinkel, Jasmina Bogojeska, Jacques Fellay, Volker Roth, Yik Lim Kok, Christian Thorball, Alessandro Borghesi, Sonali Parbhoo, Mario Wieser, Jurg Boni, Matthieu Perreau, Thomas Klimkait, Sabine Yerly, Manuel Battegay, Andri Rauch, Matthias Hoffmann, Enos Bernasconi, Matthias Cavassini, Roger Kouyos, Karin Metzner, Huldrych F. Guenthard. In Nature Communications 2019, 10, 3193.
Bayesian Markov Blanket Estimation.
Bayesian Markov Blanket Estimation.
Dinu Kaufmann, Sonali Parbhoo, Aleksander Wieczorek, Sebastian Matthias Keller, David Adametz, Volker Roth. In Proceedings AISTATS, 2016.
Workshop Publications
Workshop Publications
Informed MCMC with Bayesian Neural Networks for Facial Image Analysis.
Informed MCMC with Bayesian Neural Networks for Facial Image Analysis.
Adam Kortylewski, Mario Wieser, Andreas Morel Forster, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth, Thomas Vetter. NeurIPS Bayesian Deep Learning 2018.
Optimizing Deep Models for Interpretability.
Optimizing Deep Models for Interpretability.
Mike Wu, Sonali Parbhoo, Volker Roth, Finale Doshi-Velez. Spotlight Presentation - NeurIPS Transparent and Interpretable Machine Learning in Safety Critical Environments 2017.
Combining Kernel and Model Learning for HIV Therapy Selection.
Combining Kernel and Model Learning for HIV Therapy Selection.
Sonali Parbhoo, Jasmina Bogojeska, Volker Roth, Finale Doshi-Velez. Spotlight Presentation, Winner of IBM Best Paper for Machine Learning in Healthcare, NeurIPS ML4H 2016.
Theses and Dissertations
Theses and Dissertations
Causal Inference and Interpretable Machine Learning for Personalised Medicine.
Causal Inference and Interpretable Machine Learning for Personalised Medicine.
Sonali Parbhoo. PhD Thesis, Summa Cum Laude - University of Basel, July 2019.
A Reinforcement Learning Design for HIV Clinical Trials.
A Reinforcement Learning Design for HIV Clinical Trials.
Sonali Parbhoo. MSc. Dissertation, Completed with Distinction - University of the Witwatersrand, July 2014.
Get in touch with me at s.parbhoo@imperial.ac.uk
Get in touch with me at s.parbhoo@imperial.ac.uk
Page updated
Google Sites
Report abuse