Working Papers

1. Quantifying Inequality in Underreported Medical Conditions
   D. Shanmugam, K. Hou, E. Pierson
   [pdf] (under review)

2. Test-time augmentation improves efficiency in conformal prediction
   D. Shanmugam, H. Lu, S. Swaminarayan, J. Guttag
   [pdf] (under review)

3. Use large language models to promote equity
   E. Pierson*, D. Shanmugam*, R. Movva*, J. Kleinberg* … & many others!
   [pdf] (under review)

Publications

• Coarse race data conceals disparities in clinical risk score performance
  R. Movva*, D. Shanmugam*, K. Hou, P. Pathak, J. Guttag, N. Garg, E. Pierson
  Machine Learning for Healthcare Conference 2023
  [pdf, code]

• A multi-site study of the relationship between photoperiod and ovulation rate using NaturalCycles data
  D. Shanmugam, M. Espinosa, J. Gassen, A. van Lamsweerde, JT Pearson, E. Benhar, S. Hill
  Nature Scientific Reports 2023
  [pdf]

• Kaleidoscope: Semantically-grounded, context-specific ML model evaluation
  H. Suresh, D. Shanmugam, T. Chen, A. Bryan, A. D’Amour, J. Guttag, A. Satyanarayan
  Conference on Human Factors in Computing Systems 2023
  [pdf]

• Learning to Limit Data Collection for Data Minimization via Scaling Laws: A Computational Interpretation for the Legal Principle of Data Minimization
  D. Shanmugam, S. Shabanian, F. Diaz, M. Finck, A. Biega
  Fairness, Accountability and Transparency Conference 2022
  [pdf, supp, code]

• Data Augmentation for Electrocardiograms
  A. Raghu, D. Shanmugam, E. Pomerantsev, J. Guttag, C. Stultz
  Conference on Health, Inference, and Learning 2022
  [pdf, code]

• Better Aggregation in Test-Time Augmentation
  D. Shanmugam, D. Blalock, G. Balakrishnan, J. Guttag
  International Conference on Computer Vision 2021
  [pdf, supp, slides, code] Oral Presentation

• Multiple Instance Learning for ECG Risk Stratification
  D. Shanmugam, D. Blalock, J. Guttag
  Machine Learning in Healthcare Conference 2019
  [pdf, slides] Oral Presentation

Workshop Papers

• At the Intersection of Deep Learning and Conceptual Art: The End of Signature
  D. Shanmugam*, K. Lewis*, Jose Javier Gonzalez-Ortiz*, Agnieszka Kurant, John Guttag
  Broadening Research Collaborations Workshop, Neurips 2022
  [pdf]

• Improved Text Classification via Test-Time Augmentation
  H. Lu, D. Shanmugam, H. Suresh, J. Guttag
  UpdatableML Workshop, ICML 2020
  [pdf]

• Unsupervised Domain Adaptation in the Absence of Source Data
  R. Sahoo*, D. Shanmugam*, J. Guttag
  Uncertainty & Robustness in Deep Learning Workshop, ICML 2020
  [pdf]

• Automated Image Segmentation of Liver Stage Malaria Infection
  AP. Soleimany, H. Suresh, JJG. Ortiz, D. Shanmugam, N. Gural, J. Guttag, SN. Bhatia
  Computational Biology Workshop ICML 2019
  [pdf]

• A Convolutional Approach to Multivariate Time Series Comparison
  D. Shanmugam, D. Blalock, J. Guttag: Jiffy
  Women in Machine Learning Workshop 2017
  [pdf]

• Disparities in the performance of Natural Language Processing Tools
  H. Suresh, D. Shanmugam
  Women in Machine Learning Workshop 2017
  [poster]

Preprints

“Nothing stinks like a pile of unpublished writing” - Sylvia Plath, The Bell Jar

• More than One Way to Train a Net: Predicting Ovulation using Multiple Proxies
  D. Shanmugam, S. Hill, J. Guttag

• When and Why Test-Time Augmentation Works
  D. Shanmugam, D. Blalock, G. Balakrishnan, J. Guttag
  [pdf]

• Addressing Feature-Dependent Label Noise: A Generative Framework
  J. Sahota, D. Shanmugam J. Ramanan, S. Eghbali, M. Brubaker
  [pdf]