Divyat Mahajan

Zero-Shot Learning of Causal Models With the increasing acquisition of datasets over time, we now have access to precise and varied descriptions of the world, capturing all sorts of phenomena. These datasets can be seen as empirical obs...

Zero-Shot Learning of Causal Models

📜 arxiv.org/abs/2410.06128

💬 Causal Rep. Learning Workshop (15th Dec)

TLDR: Amortized SCM learning to enable zero-shot generation of novel observational and interventional samples

Compositional Risk Minimization In this work, we tackle a challenging and extreme form of subpopulation shift, which is termed compositional shift. Under compositional shifts, some combinations of attributes are totally absent from ...

Compositional Risk Minimization

📜 arxiv.org/abs/2410.06303

💬 Compositional Learning Workshop (15th Dec)

TLDR: Provable method for extrapolating classifiers to novel combinations of attributes

I am at #NeurIPS2024 this week, presenting our recent works at the compositional learning workshop and the causal representation learning workshop.