Author

S. Natarajan

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

A Compositional Theory of Curvature in Probabilistic Circuits

Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface curvature: the trace of the Hessian of the log-likelihood. Recent work regularizes this trace globally to bias learning toward flatter, better generalizi...

Hrithik Suresh, Sahil Sidheekh, Shelar Parth Vijay et al. · 0 citations

Preprint Aug 2026

Tydra: An Efficient Hybrid Model for Tabular Data

Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subquadratic SSM-based alternatives such as Hydra trade away accuracy for efficiency. To balance both, we introduce Tydra, a hybrid Transformer-...

Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus et al. · 0 citations

#artificial intelligence Conference Feb 2024

Building Expressive and Tractable Probabilistic Generative Models: A Review

A unified perspective on the inherent trade-offs between expressivity and tractability is provided, highlighting the design principles and algorithmic extensions that have enabled building expressive and efficient PCs, and a taxonomy of the field is provided.

Sahil Sidheekh, S. Natarajan · International Joint Conferen... · 13 citations