135 citations · 307 across the 31 of their papers we have counts for
7 papers · 1 filter
Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference
Akshay Vyas, Hailiang Dong, Shivvrat Arya +4
Probabilistic graphical models (PGMs) compactly encode structured joint distributions, but Most Probable Explanation (MPE), which finds the highest-probability assignment to unobse…
Learning to Condition: A Neural Heuristic for Scalable MPE Inference
Brij Malhotra, Shivvrat Arya, Tahrima Rahman +1
We introduce learning to condition (L2C), a scalable, data-driven framework for accelerating Most Probable Explanation (MPE) inference in Probabilistic Graphical Models (PGMs), a f…
Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification
Shivvrat Arya, Yu Xiang, Vibhav Gogate
We present a unified framework called deep dependency networks (DDNs) that combines dependency networks and deep learning architectures for multi-label classification, with a parti…
Learning to Solve the Constrained Most Probable Explanation Task in Probabilistic Graphical Models
Shivvrat Arya, Tahrima Rahman, Vibhav Gogate
We propose a self-supervised learning approach for solving the following constrained optimization task in log-linear models or Markov networks. Let and be two log-linear mo…
Neural Network Approximators for Marginal MAP in Probabilistic Circuits
Shivvrat Arya, Tahrima Rahman, Vibhav Gogate
Probabilistic circuits (PCs) such as sum-product networks efficiently represent large multi-variate probability distributions. They are preferred in practice over other probabilist…
Deep Dependency Networks for Multi-Label Classification
Shivvrat Arya, Yu Xiang, Vibhav Gogate
We propose a simple approach which combines the strengths of probabilistic graphical models and deep learning architectures for solving the multi-label classification task, focusin…
Domain Aware Markov Logic Networks
Happy Mittal, Ayush Bhardwaj, Vibhav Gogate +1
Combining logic and probability has been a long stand- ing goal of AI research. Markov Logic Networks (MLNs) achieve this by attaching weights to formulas in first-order logic, and…