Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models

Oliver Ethan Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D Viviano, Abdessamad El Kabid, Ali Parviz, Yoshua Bengio

TL;DR: we unify and generalize many key algorithms in AI by augmenting probabilistic dependency graphs with attention and control.

Abstract:

We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a subset of the model and resolve inconsistencies using the parameters under control. This framework, which we call Local Inconsistency Resolution (LIR) is built upon Probabilistic Dependency Graphs (PDGs), which provide a flexible representational foundation capable of capturing inconsistent beliefs. We show how LIR unifies and generalizes a wide variety of important algorithms in the literature, including the Expectation-Maximization (EM) algorithm, belief propagation, adversarial training, GANs, and GFlowNets.
In the last case, LIR actually suggests a more natural loss, which we demonstrate improves GFlowNet convergence.
Each of these methods can be recovered as a specific instance of LIR by choosing a procedure to direct focus (attention and control). We implement this algorithm for discrete PDGs and study its properties on synthetically generated PDGs, comparing its behavior to the global optimization semantics of the full PDG.

Code Dataset Promise: No

Format Confirmation: I agree that I have read and followed the formatting instructions for the camera ready version.

Submission Number: 1791