On Faster Marginalization with Squared Circuits via Orthonormalization
Not on the map. Why?
Abstract (arXiv)
Squared tensor networks (TNs) and their generalization as parameterized computational graphs -- squared circuits -- have been recently used as expressive distribution estimators in high dimensions. However, the squaring operation introduces additional complexity when marginalizing variables or computing the partition function, which hinders their usage in machine learning applications. Canonical forms of popular TNs are parameterized via unitary matrices as to simplify the computation of particular marginals, but cannot be mapped to general circuits since these might not correspond to a known TN. Inspired by TN canonical forms, we show how to parameterize squared circuits to ensure they encode already normalized distributions. We then use this parameterization to devise an algorithm to compute any marginal of squared circuits that is more efficient than a previously known one. We conclude by formally showing the proposed parameterization comes with no expressiveness loss for many circuit classes.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 39 references that are in the map. First posted on arXiv 10 Dec 2024.
Builds on
15 of 39 references.
References · 15
- 2015Unitary Evolution Recurrent Neural Networkscited by 291
- 2019Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Groupcited by 133
- 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
- 2017Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networkscited by 92
- 2022An Introduction to Neural Data Compressioncited by 78
- 2023Tractable Control for Autoregressive Language Generationcited by 65
- 2019Tree Tensor Networks for Generative Modelingcited by 63
- 2019Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learningcited by 55
- 2023Subtractive Mixture Models via Squaring: Representation and Learningcited by 39
- 2018From probabilistic graphical models to generalized tensor networks for supervised learningcited by 31
- 2021Tensor-Train Density Estimationcited by 30
- 2023How to Turn Your Knowledge Graph Embeddings into Generative Modelscited by 20
Built on by
Citing papers per year: 2025: 2.
2 papers.