From aab516362cd85c74754494e98770300b0e690cc6 Mon Sep 17 00:00:00 2001 From: loreloc Date: Fri, 3 Jan 2025 18:07:07 +0100 Subject: [PATCH] add ref to colorai in news --- _news/aaai2025.md | 4 ++-- _publications/loconte2024faster.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/_news/aaai2025.md b/_news/aaai2025.md index 3516799..6e781f0 100644 --- a/_news/aaai2025.md +++ b/_news/aaai2025.md @@ -1,7 +1,7 @@ --- -title: "One paper accepted at AAAI 2025" +title: "Two papers accepted at AAAI 2025 and CoLoRAI" collection: news permalink: /news/aaai-2025 date: 2024-12-10 --- -Our paper on sum of squares circuits is accepted at AAAI 2025. +Our paper on sum of squares circuits is accepted at AAAI 2025, and our work on speeding up marginalization with squared circuits will be presented at the CoLoRAI workshop at AAAI. diff --git a/_publications/loconte2024faster.md b/_publications/loconte2024faster.md index d2a4374..58896f9 100644 --- a/_publications/loconte2024faster.md +++ b/_publications/loconte2024faster.md @@ -9,7 +9,7 @@ image: "/images/papers/loconte2024faster/mar-squared-circuit.png" authors: "Lorenzo Loconte, Antonio Vergari" paperurl: "https://arxiv.org/abs/2412.07883" pdf: "https://arxiv.org/abs/2412.07883" -venue: "arXiv 2024" +venue: "CoLoRAI 2025" excerpt: " Inspired by canonical forms in tensor networks, we devise sufficient conditions to ensure squared circuits are already normalized and then devise a more efficient marginalization algorithm." abstract: "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." supplemental: