Saved in:
Bibliographic Details
Main Authors: Li, Yun-Peng, Loeliger, Hans-Andrea
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.12113
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910917125472256
author Li, Yun-Peng
Loeliger, Hans-Andrea
author_facet Li, Yun-Peng
Loeliger, Hans-Andrea
contents Normals with unknown parameters (NUP) can be used to convert nontrivial model-based estimation problems into iterations of linear least-squares or Gaussian estimation problems. In this paper, we extend this approach by augmenting factor graphs with convex-dual variables and pertinent NUP representations. In particular, in a state space setting, we propose a new iterative forward-backward algorithm that is dual to a recently proposed backward-forward algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual NUP Representations and Min-Maximization in Factor Graphs
Li, Yun-Peng
Loeliger, Hans-Andrea
Machine Learning
Systems and Control
Signal Processing
Normals with unknown parameters (NUP) can be used to convert nontrivial model-based estimation problems into iterations of linear least-squares or Gaussian estimation problems. In this paper, we extend this approach by augmenting factor graphs with convex-dual variables and pertinent NUP representations. In particular, in a state space setting, we propose a new iterative forward-backward algorithm that is dual to a recently proposed backward-forward algorithm.
title Dual NUP Representations and Min-Maximization in Factor Graphs
topic Machine Learning
Systems and Control
Signal Processing
url https://arxiv.org/abs/2501.12113