9 papers
Environment-Robust Representation Learning with Empirical Bayes
Yuli Slavutsky, Matthew Shen, Bohan Wu +1
We consider multi-environment prediction problems. We assume the environments change the distribution of a latent variable, while the mechanisms generating observed covariates and…
Robust Representation Learning through Explicit Environment Modeling
Yuli Slavutsky, David M. Blei
We consider learning from labeled data collected across multiple environments, where the data distribution may vary across these environments. This problem is commonly approached f…
Neural Generalized Mixed-Effects Models
Yuli Slavutsky, Sebastian Salazar, David M. Blei
Generalized linear mixed-effects models (GLMMs) are widely used to analyze grouped and hierarchical data. In a GLMM, each response is assumed to follow an exponential-family distri…
Input Adaptive Bayesian Model Averaging
Yuli Slavutsky, Sebastian Salazar, David M. Blei
This paper studies prediction with multiple candidate models, where the goal is to combine their outputs. This task is especially challenging in heterogeneous settings, where diffe…
Quantifying Uncertainty in the Presence of Distribution Shifts
Yuli Slavutsky, David M. Blei
Neural networks make accurate predictions but often fail to provide reliable uncertainty estimates, especially under covariate distribution shifts between training and testing. To…
Variational Learning of Disentangled Representations
Yuli Slavutsky, Ozgur Beker, David Blei +1
Disentangled representations separate factors that are shared across conditions from those that are condition-specific. Such separation is needed for generalization to new domains,…
CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models
Eitan Wagner, Yuli Slavutsky, Omri Abend
Although language model scores are often treated as probabilities, their reliability as probability estimators has mainly been studied through calibration, overlooking other aspect…
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
Yuli Slavutsky, Yuval Benjamini
Zero-shot learning methods typically assume that the new, unseen classes encountered during deployment come from the same distribution as the the classes in the training set. Howev…
Predicting Classification Accuracy When Adding New Unobserved Classes
Yuli Slavutsky, Yuval Benjamini
Multiclass classifiers are often designed and evaluated only on a sample from the classes on which they will eventually be applied. Hence, their final accuracy remains unknown. In…