6 papers
A Compositional Theory of Curvature in Probabilistic Circuits
Hrithik Suresh, Sahil Sidheekh, Shelar Parth Vijay +3
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: th…
A Probabilistic Circuit-Induced Pseudo-Metric for Out-of-Distribution Detection
Bhumika K, Vidhya S, Narayanan C Krishnan
Probabilistic Circuits (PCs) are tractable generative models whose internal nodes encode a hierarchy of probabilistic summaries over different variable scopes. Existing PC-based ou…
Diverse and Plausible Algorithmic Recourse via Tractable Recourse Distributions
Anagha Sabu, Hrithik Suresh, Narayanan C. Krishnan
Algorithmic recourse seeks to help individuals reverse unfavorable automated decisions by recommending actionable changes that achieve a desired outcome. As an individual usually h…
PAR: Plausibility-aware Amortized Recourse Generation
Anagha Sabu, Vidhya S, Narayanan C Krishnan
Algorithmic recourse aims to recommend actionable changes to a factual's attributes that flip an unfavorable model decision while remaining realistic and feasible. We formulate rec…
Learning Regularizers: Learning Optimizers that can Regularize
Suraj Kumar Sahoo, Narayanan C Krishnan
Learned Optimizers (LOs), a type of Meta-learning, have gained traction due to their ability to be parameterized and trained for efficient optimization. Traditional gradient-based…
Tractable Sharpness-Aware Learning of Probabilistic Circuits
Hrithik Suresh, Sahil Sidheekh, Vishnu Shreeram M. P +2
Probabilistic Circuits (PCs) are a class of generative models that allow exact and tractable inference for a wide range of queries. While recent developments have enabled the learn…