From 8f7e8e036e9dfc53a5c085b5cb8d7ddda7c34db7 Mon Sep 17 00:00:00 2001
From: Charles Dickens <charlieadickens@gmail.com>
Date: Wed, 8 May 2024 08:42:59 -0700
Subject: [PATCH] Update dickens-arxiv24 to dickens-icml24.

---
 .../{dickens-arxiv24.json => dickens-icml24.json}   |   8 +++++---
 .../{dickens-arxiv24.pdf => dickens-icml24.pdf}     | Bin
 2 files changed, 5 insertions(+), 3 deletions(-)
 rename _data/pubs/{dickens-arxiv24.json => dickens-icml24.json} (88%)
 rename assets/resources/{dickens-arxiv24.pdf => dickens-icml24.pdf} (100%)

diff --git a/_data/pubs/dickens-arxiv24.json b/_data/pubs/dickens-icml24.json
similarity index 88%
rename from _data/pubs/dickens-arxiv24.json
rename to _data/pubs/dickens-icml24.json
index eff505c..5a10b3d 100644
--- a/_data/pubs/dickens-arxiv24.json
+++ b/_data/pubs/dickens-icml24.json
@@ -1,5 +1,5 @@
 {
-  "type": "unpublished",
+  "type": "conference",
   "title": "Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning",
   "authors": [
     "Charles Dickens",
@@ -8,12 +8,14 @@
     "Stephen Wright",
     "Lise Getoor"
   ],
-  "venue": "arXiv",
+  "venue": "International Conference on Machine Learning",
   "year": "2024",
+  "publisher": "PMLR",
+  "address": "Vienna Austria",
   "links": [
     {
       "label": "paper",
-      "href": "/assets/resources/dickens-arxiv24.pdf"
+      "href": "/assets/resources/dickens-icml24.pdf"
     }
   ],
   "abstract": "We address a key challenge for neuro-symbolic (NeSy) systems by leveraging convex and bilevel optimization techniques to develop a general gradient-based framework for end-to-end neural and symbolic parameter learning. The applicability of our framework is demonstrated with NeuPSL, a state-of-the-art NeSy architecture. To achieve this, we propose a smooth primal and dual formulation of NeuPSL inference and show learning gradients are functions of the optimal dual variables. Additionally, we develop a dual block coordinate descent algorithm for the new formulation that naturally exploits warm-starts. This leads to over 100× learning runtime improvements over the current best NeuPSL inference method. Finally, we provide extensive empirical evaluations across 8 datasets covering a range of tasks and demonstrate our learning framework achieves up to a 16% point prediction performance improvement over alternative learning methods.",
diff --git a/assets/resources/dickens-arxiv24.pdf b/assets/resources/dickens-icml24.pdf
similarity index 100%
rename from assets/resources/dickens-arxiv24.pdf
rename to assets/resources/dickens-icml24.pdf