I am a Postdoctoral Fellow at the Vector Institute, in Toronto, Ontario where I primarily work with Anna Goldenberg, Marzyeh Ghassemi, and Frank Rudzicz. I received my PhD in Electrical and Computer Engineering Department at the University of Texas at Austin (UT, Austin). I was advised by Dr. Joydeep Ghosh, director of IDEAL at UT, Austin. I was also affliciated with WNCG. Prior to joining UT, I worked with Amazon Lab126 for two years, prototyping and developing interesting application and platform software using Machine Learning, Image Processing and Computer Vision for next generation consumer products. I completed my Masters from University of California, San Diego, majoring in Computer Engineering in 2011. My research is broadly focused on building reliable, fair, interpretable clinical machine learning models. For more details, my CV is available here.


  • 03/17/20: Guest Lecture: (on Fairness, Explainability in ML) AI and Society Class at McMaster University

  • 01/23/20: Guest Lecture: (on Causal Inference) Machine Learning for Health Graduate Class of UofT, CS

  • 11/26/19: Guest Lecture: AI and Ethics Graduate Class of UofT, CS

  • 11/22/19: Invited Talk: Healthcare Disparity and AI with the 99 AI Challenge cohort with the University of Toronto Libraries

  • 11/08/19: Invited Talk: Explainability and Fairness in Health at the CSI Departmental Seminar, Emory University

  • 10/11/19: Invited Talk: Data & Society Meeting on Evaluating Fairness for ML in Health

  • 10/01/19: 3 Workshop papers accepted at the NeurIPS ML4H and Fair ML for Health workshops

  • 08/26/19: I gave a talk at the launch of the Schwartz Reisman Institute for Technology and Society (SRIT&S) on fairness and explainability in health

  • 07/23/19: Co-chairing the Fair ML for Health workshop at NeurIPS 2019.

Shalmali Joshi

shalmali at vectorinstitute dot ai

Vector Institute
Toronto, ON

Google Scholar


Conference and Journal

  • Irene Chen and Shalmali Joshi and Marzyeh Ghassemi (2020), "Treating Health Disparities with Artificial Intelligence" , In Nature Medicine.
  • McCradden M and Shalmali Joshi and James Anderson and Mjaye Mazwi (2020), "When your only tool is a hammer: Ethical Limitations of Computational Fairness Solutions in Healthcare Machine Learning (Oral)", In AAAI Conference on AI Ethics and Society (AIES).
  • Shalmali Joshi*, Tonekaboni* S, McCradden M and Goldenberg A (2019), "What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use", In Machine Learning for Healthcare.
  • Shalmali Joshi, Khanna R and Ghosh J (2018), "Co-regularized Monotone Regtargeting for Semi-supervised LeTOR", In Siam International Conference on Data Mining (SDM).


  • Shalmali Joshi, Gunasekar S, Sontag D and Ghosh J (2016), "Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization", In Machine Learning for Healthcare Conference., 10 December, 2016., pp. 17-41. jmlr.org.
  • Shalmali Joshi, Ghosh J, Reid M and Koyejo O (2016), "Rényi divergence minimization based co-regularized multiview clustering", Machine Learning, 1 September, 2016. Vol. 104(2-3), pp. 411-439. Springer US.
  • Shalmali Joshi, Koyejo O and Ghosh J (2015), "Simultaneous Prognosis of Multiple Chronic Conditions from Heterogeneous EHR Data", In 2015 International Conference on Healthcare Informatics., October, 2015. , pp. 497-497. ieeexplore.ieee.org.

Peer reviewed workshops

  • Tonekaboni S, Shalmali Joshi and Goldenberg A (2019), "Individualized Feature Importance for Time Series Risk Prediction Models", In Machine Learning for Health Workshop at NeurIPS.

  • McCradden M, Anderson J and Shalmali Joshi (2019), "When your only tool is a hammer: The limits of computational solutions to bias in healthcare ML", In Fair ML for Health Workshop at NeurIPS.

  • Yi S, Wang S, Shalmali Joshi and Ghassemi M (2019), "Fair and Robust Treatment Effect Estimates: Estimation Under Treatment and Outcome Disparity with Deep Neural Models", In Fair ML for Health Workshop at NeurIPS.

  • McCradden M, Tonekaboni S, Shalmali Joshi and Goldenberg A (2019), "Five Pillars of Explainable Clinical Machine Learning", In Frontier of AI-Assisted Care (FAC) Scientific Symposium.

  • Shalmali Joshi, Koyejo O, Kim B, Vijitbenjaronk W and Ghosh J (2019), "Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems", In SafeML Workshop at the International Conference on Learning Representations.

  • Shalmali Joshi, Kim B, Koyejo O and Ghosh J (2017), "Through the looking GANs", In Women in Machine Learning Workshop @ NIPS.

  • Shalmali Joshi, Koyejo O and Ghosh J (2014), "Multiview Clustering via Constrained Bayesian Inference", In Workshop on Divergence Methods for Probabilistic Inference @ International Conference on Machine Learning (ICML).


  • Shalmali Joshi (2018), "Constraint based Approaches to Interpretable and Semi-Supervised Machine Learning". Thesis at: The University of Texas at Austin., December, 2018.

Work Experience

  • Nov '18-current, Vector Institute, Postdoctoral Fellow
  • 2013-2015, Amazon Lab126, Software Engineer
  • Summer, 2015, Yahoo! Labs, Technical Intern
Teaching Assistant
  • Fall 2015, Advanced Predictive Modeling, McCombs School of Business at UT Austin
  • Fall 2014, Graduate Data Mining, Electrical and Computer Engg. at UT Austin
  • Spring 2014, Graduate Data Mining, Electrical and Computer Engg. at UT Austin
Plain Academic