Birs- 24w5284: Statistical Aspects of Trustworthy Machine Learning

  1. Title:
    Interpretability and Scientific Foundation Models: A Review

    Speaker:

    Link:

  2. Title:
    Simpler Machine Learning Models for a Complicated World

    Speaker:

    Link:

  3. Title:
    Deep non-crossing quantile (NQ) learning

    Speaker:

    Link:

  4. Title:
    A Class of Dependent Random Distributions Based on Atom Skipping

    Speaker:

    Link:

  5. Title:
    Interpretable machine learning for time-to-event prediction in medicine and healthcare

    Speaker:

    Link:

  6. Title:
    Estimating the fraction of anomaly points

    Speaker:

    Link:

  7. Title:
    Generative AI on Smooth Manifolds: A Tutorial

    Speaker:

    Link:

  8. Title:
    What is uncertainty in today's practice of data science?

    Speaker:

    Link:

  9. Title:
    Teaching Machine Learning using Data for Good

    Speaker:

    Link:

  10. Title:
    Online Local Differential Private Quantile Inference via Self-normalization

    Speaker:

    Link:

  11. Title:
    A decorrelation method for general regression adjustment in randomized experiments

    Speaker:

    Link:

  12. Title:
    CATE: An accelerated and scalable solution for large-scale genomic data processing through GPU and CPU-based parallelization

    Speaker:

    Link:

  13. Title:
    eXplainable representation learning via Autoencoders revealing Critical genes

    Speaker:

    Link:

  14. Title:
    Algorithmic Fairness; Why it’s hard and why it’s interesting (Tutorial)

    Speaker:

    Link:

  15. Title:
    De-Biasing the Bias: Methods for Improving Disparity Assessments with Noisy Group Measurements

    Speaker:

    Link:

  16. Title:
    A Generic Approach to Stabilized Model Distillation

    Speaker:

    Link:

  17. Title:
    Conditional independence measures for fairer, more reliable models

    Speaker:

    Link:

  18. Title:
    Protecting Individua Privacy against All Adversaries – Is It possible?

    Speaker:

    Link:

  19. Title:
    Forgettable Federated Linear Learning with Certified Data Removal

    Speaker:

    Link:

  20. Title:
    PANORAMIA: Efficient Privacy Auditing of Machine Learning Models without Retraining

    Speaker:

    Link: