Search Results for author:
Found 5 papers, 2 papers with code
Causally Inspired Regularization Enables Domain General Representations
Given a causal graph representing the data-generating process shared across different domains/distributions, enforcing sufficient graph-implied conditional independencies can identify domain-general (non-spurious) feature representations.
ImageNot: A contrast with ImageNet preserves model rankings
We introduce ImageNot, a dataset designed to match the scale of ImageNet while differing drastically in other aspects.
Proxy Methods for Domain Adaptation
We study the problem of domain adaptation under distribution shift, where the shift is due to a change in the distribution of an unobserved, latent variable that confounds both the covariates and the labels.
Target Conditioned Representation Independence (TCRI); From Domain-Invariant to Domain-General Representations
We propose a Target Conditioned Representation Independence (TCRI) objective for domain generalization.
Adapting to Latent Subgroup Shifts via Concepts and Proxies
We show that the optimal target predictor can be non-parametrically identified with the help of concept and proxy variables available only in the source domain, and unlabeled data from the target.
