DeepFlow: Two Convergent Differentiable Approaches for Pairwise Conditional Random Fields

arXiv:2610.16546v1 Announce Type: new Abstract: Basic probabilistic models form the basis of modern deep learning largely by defining the final activation layer of a network and allowing the networks outputs to be interpreted through a probabilistic lens. By increasing the complexity of these final activation layers to include features such as spatial regularisation, allow for these models to improve in performance without requiring significantly more data. The challenge however is to ensure that these more complex probabilistic graphical models adapt well to being used in tandem with deep learning, that is, ensuring they converge and have meaningful derivatives. The goal of this paper is to show two algorithms with provable convergence properties to allow this type of regularisation for image and signal classification models. Through both rigorous mathematical analysis and in silico experiments, we can show the differing performance between these solution types.

Related

• Embedding Linear Equality Constraints in Probabilistic Neural Networks for Dynamic Modelling
• Efficient Autoregressive Inference for Transformer Probabilistic Models
• On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions

Source: arXiv cs.LG | 2026-10-14