SyncAI.news, a Varaisys broadcasting
Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP
AV

Akshay Vyas, Shivvrat Arya, Brij Malhotra, Tahrima Rahman, Vibhav Gogate, Nicholas Ruozzi

· 1 min read

ResearcharXiv cs.LG

Neural Dual Bounds: Valid-by-Construction JGLP Warm-Starts for MAP and Constrained MAP

arXiv:2611.19218v1 Announce Type: new Abstract: We present Neural Dual Bounds, a calibration-free framework that produces deterministic upper bounds for MAP inference in probabilistic graphical models using a single neural-network forward pass. The framework trains a network to output the edge messages of a mini-bucket style upper bound on a given join-graph decomposition in a self-supervised manner by directly minimizing a smooth dual objective. The output of this network can be used at test time to warm-start a standard JGLP optimizer. Across diverse benchmarks, this warm start yields dual gaps that are orders of magnitude tighter than those from zero initialization, with the largest gains in the early-iteration regime. We also apply our framework for the constrained MAP (CMPE) task, where neural warm starts with test-time adaptation are comparable to the adaptive baseline on Bayesian networks and achieve the tightest dual gaps, by one to two orders of magnitude, on the grid and segmentation families.

Original source

This story was published by arXiv cs.LG and written by Akshay Vyas, Shivvrat Arya, Brij Malhotra, Tahrima Rahman, Vibhav Gogate, Nicholas Ruozzi. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News