Search Results for author:
Found 3 papers, 2 papers with code
Ask Your Distribution Shift if Pre-Training is Right for You
In particular, we focus on two possible failure modes of models under distribution shift: poor extrapolation (e. g., they cannot generalize to a different domain) and biases in the training data (e. g., they rely on spurious features).
Hot PATE: Private Aggregation of Distributions for Diverse Task
Moreover, the knowledge of models is often encapsulated in the response distribution itself and preserving this diversity is critical for fluid and effective knowledge transfer from teachers to student.
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation
We apply our decomposition framework to three scenarios -- well-specified, misspecified, and corrected models -- to 1) choose between labeled and unlabeled data and 2) learn from their combination.
