Home /  [Virtual] Hot Topics: Foundations of Stable, Generalizable and Transferable Statistical Learning

Workshop

[Virtual] Hot Topics: Foundations of Stable, Generalizable and Transferable Statistical Learning March 07, 2022 - March 10, 2022
Parent Program: --
Series: Hot Topic, Hot Topic
Location: SLMath: Online/Virtual
Organizers LEAD Peter Bühlmann (ETH Zurich), John Duchi (Stanford University), Elizabeth Tipton (Northwestern University), Bin Yu (University of California, Berkeley)
Speaker(s)

Show List of Speakers

Description
Image
When data automatically drop from the sky: intelligent approaches in data science change the way humans and computers interact. (Illustration: Niklas Briner)
Despite the remarkable success in extracting information from complex and (often) large-scale datasets over the last two decades, further progress is needed to making automated statistical and machine learning algorithms more reliable, robust, interpretable and trustworthy. This workshop has its focus on foundational aspects of this goal, linking areas at the interface between statistics, optimization, machine learning and computer science, such as distributional robustness and stability, adversarial and transfer learning, generalizability and meta analysis, and causality.
Keywords and Mathematics Subject Classification (MSC)
Tags/Keywords
  • Artificial Intelligence

  • data science

  • machine learning

  • optimization

  • Stochastic Modeling

  • statistics

Primary Mathematics Subject Classification
Secondary Mathematics Subject Classification No Secondary AMS MSC
Schedule, Notes/Handouts & Videos
Show Schedule, Notes/Handouts & Videos
Show All Collapse
Mar 07, 2022
Monday
07:55 AM - 08:00 AM
  Welcome
08:00 AM - 08:25 AM
  Datamodels: Predicting Predictions with Training Data
Aleksander Madry (Massachusetts Institute of Technology)
08:30 AM - 08:55 AM
  Domain Adaptation Under Structural Causal Models
Yuansi Chen (Duke University )
09:00 AM - 09:25 AM
  Assessing Replicability Via Multi-lab Collaborations
Blake McShane (Northwestern University)
09:30 AM - 10:00 AM
  Lunch / Dinner Break
10:00 AM - 10:25 AM
  Elements of External Validity: Framework, Design, and Analysis
Erin Hartman (University of California, Berkeley)
10:30 AM - 10:55 AM
  Evaluating Replicability: Considerations for Analyses and Implications for Design
Jacob Schauer (Northwestern University)
11:00 AM - 11:15 AM
  Break
11:15 AM - 12:15 PM
  Discussion
Mar 08, 2022
Tuesday
08:00 AM - 08:25 AM
  Disentangling Confounding and Nonsense Associations Due to Dependence
Betsy Ogburn (Johns Hopkins University)
08:30 AM - 08:55 AM
  Interpretable Sensitivity Analysis for the Baron–Kenny Approach to Mediation with Unmeasured Confounding
Peng Ding (University of California, Berkeley)
09:00 AM - 09:25 AM
  Distribution Generalization in Underidentified Causal Models
Jonas Peters (University of Copenhagen)
09:30 AM - 10:00 AM
  Lunch / Dinner Break
10:00 AM - 10:25 AM
  An Automatic Finite-Sample Robustness Metric: Can Dropping a Little Data Change Conclusions?
Tamara Broderick (Massachusetts Institute of Technology)
10:30 AM - 10:55 AM
  Near-Optimal Compression in Near-Linear Time
Raaz Dwivedi (Harvard University)
11:00 AM - 11:15 AM
  Break
11:15 AM - 12:15 PM
  Discussion
Mar 09, 2022
Wednesday
08:00 AM - 08:25 AM
  A Precise High-Dimensional Asymptotic Theory for AdaBoost
Pragya Sur (Harvard University)
08:30 AM - 08:55 AM
  Prospects and Perils of Interpolating Models
Fanny Yang
09:00 AM - 09:25 AM
  Distributionally Robust Bayesian Nonparametric Regression
Jose Blanchet (Stanford University)
09:30 AM - 10:00 AM
  Lunch / Dinner Break
10:00 AM - 10:25 AM
  Calibrated Inference: Statistical Inference that Accounts for Both Sampling Uncertainty and Distributional Uncertainty
Dominik Rothenhaeusler (Stanford University)
10:30 AM - 10:55 AM
  Assessing External Validity Over Worst-Case Subpopulations
Hongseok Namkoong (Columbia University)
11:00 AM - 11:15 AM
  Break
11:15 AM - 12:15 PM
  Discussion
Mar 10, 2022
Thursday
08:00 AM - 08:25 AM
  Veridical Network Embedding
Tian Zheng (Columbia University)
08:30 AM - 08:55 AM
  Bayesian Nonparametric Models for Treatment Effect Heterogeneity: Model Parameterization, Prior Choice, and Posterior Summarization
Jared Murray (University of Texas, Austin)
09:00 AM - 09:25 AM
  Sim2Real Transfer in Robotics: Thoughts on Model Pruning and Robust Visual Transfer
Bradly Stadie (Toyota technological Institute at Chicago)
09:30 AM - 10:00 AM
  Lunch / Dinner Break
10:00 AM - 10:25 AM
  Predicting Out-of-Distribution Error with the Projection Norm
Jacob Steinhardt (UC Berkeley)
10:30 AM - 10:55 AM
  Structured Adaptation & Deep Learning: When Prediction Yields Adaptation
Zachary Lipton (Carnegie Mellon University)
11:00 AM - 11:15 AM
  Break
11:15 AM - 12:15 PM
  Discussion