Sirisha Rambhatla

Theory-guided Machine Learning for the Real World

CPH 4358, 200 University Ave. W., Waterloo, ON, Canada



I am an Assistant Professor at the University of Waterloo with appointments in the

I lead the Critical ML lab at the University of Waterloo. I am also affiliated with:

More details about my background at here: Curriculum Vitae

Areas of Interests

| Statistical Machine Learning | Sparse Signal Processing | Spatiotemporal Data Analysis | AI for Surgery and Healthcare | Interpretability of Deep Learning Models | Intelligent Automation and Manufacturing | Computer Vision |

news

Oct 27, 2023 Our work on Are all classes created equal? Domain Generalization for Domain-Linked Classes is accepted to the DistShift Workshop at NeurIPS 2023. :star:
Aug 10, 2023 Our work on domain-guided spatio-temporal transformers for egocentric 3D pose estimation is accepted at KDD 2023. :star:
Feb 2, 2023 Do we really need stylization for Domain Adaptation, our workshop paper at the DistShift Workshop at ICLR 2023 investigates this question and develop a simple implicit stylization for domain adaptation. :star:
Jun 6, 2022 Our work on spatio-temporal transformers for egocentric 3D pose estimation is accepted for oral presentation in the EPIC and Ego4D workshop at CVPR 2022. :star:
Mar 30, 2022 My work in collaboration with UHN, Toronto on forecasting trajectories of the waitlisted NASH patients using deep learning has been accepted for oral presentation at the International Liver Transplant Society’s annual meeting! :star:

selected publications

  1. ICLR
    🏆 Travel Award
    NOODL: Provable Online Dictionary Learning and Sparse Coding
    Rambhatla, S., Li, X., and Haupt, J.
    International Conference on Learning Representations (ICLR) 2019
  2. NeurIPS
    Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning
    Rambhatla, S., Li, X., and Haupt, J.
    Advances in Neural Information Processing Systems (NeurIPS) 2020
  3. NeurIPS
    How does this interaction affect me? Interpretable attribution for feature interactions
    Tsang, M., Rambhatla, S., and Liu, Y.
    Advances in Neural Information Processing Systems (NeurIPS) 2020
  4. TSP
    A Dictionary-Based Generalization of Robust PCA With Applications to Target Localization in Hyperspectral Imaging
    Rambhatla, S., Li, X., Ren, J., and Haupt, J.
    IEEE Tran. on Signal Processing 2020