Divyat Mahajan
@divyat.bsky.social
Ph.D. Student at Mila
Visiting Researcher at Meta FAIR
Causality, Trustworthy ML
Former: Microsoft Research, IIT Kanpur
divyat09.github.io
Visiting Researcher at Meta FAIR
Causality, Trustworthy ML
Former: Microsoft Research, IIT Kanpur
divyat09.github.io
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
📜 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
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...
arxiv.org
December 10, 2024 at 8:21 AM
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
📜 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
📜 arxiv.org/abs/2410.06303
💬 Compositional Learning Workshop (15th Dec)
TLDR: Provable method for extrapolating classifiers to novel combinations of attributes
📜 arxiv.org/abs/2410.06303
💬 Compositional Learning Workshop (15th Dec)
TLDR: Provable method for extrapolating classifiers to novel combinations of attributes
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 ...
arxiv.org
December 10, 2024 at 8:21 AM
Compositional Risk Minimization
📜 arxiv.org/abs/2410.06303
💬 Compositional Learning Workshop (15th Dec)
TLDR: Provable method for extrapolating classifiers to novel combinations of attributes
📜 arxiv.org/abs/2410.06303
💬 Compositional Learning Workshop (15th Dec)
TLDR: Provable method for extrapolating classifiers to novel combinations of attributes