Can we use learning to obtain feasible solutions to discrete problems? "Erdős goes neural" @NeurIPS2020 (oral) proposes a differentiable way to solve combinatorial problems with unsupervised GNNs. paper: arxiv.org/abs/2006.10643 blog: bit.ly/385pJlu with Nikos Karalias

Also check out our poster for "Erdos Goes Neural"! Town C1, spot D1. Session begins in about an hour :)

Self-similarity

Graph compression is a very challenging graph machine learning problem that is relatively unexplored from a neural perspective. Join us tomorrow to hear/discuss our ideas and experiences. 📰: arxiv.org/abs/2107.01952 with Giorgos Bouritsas (@[email protected]), Nikos Karalias, Michael Bronstein

Announcing our #NeurIPS2021 paper:"Partition and Code: learning how to compress graphs", a neural graph compression framework, at the meeting point of information theory and graph machine learning. arxiv.org/abs/2107.01952 w/Andreas Loukas Nikos Karalias Michael Bronstein A thread 🧵

We will be discussing "Partition and Code" today at 4:30-6:00 pm GMT @ Gather Town, Graph Learning room, spot B0. If you are interested in graph ML and neural compression, come talk to us! #NeurIPS2021 neurips.cc/virtual/2021/p…

Jay Cummings One quite famous (and moving) example (CW: suicide):

Our paper on neural extensions of set functions arxiv.org/abs/2208.04055 has been accepted at #NeurIPS2022. Was a pleasure to work with Josh Robinson, Andreas Loukas, and Stefanie Jegelka on this one :) Thread/repo/camera-ready coming soon.

This Wednesday 2PM (PST) we will present our poster on continuous extensions of discrete functions (hall J #305 - poster session 4). I'll be here at #NeurIPS2022 all week so if you want to chat about comb opt/ML dm me :)

I'll be presenting our work on continuous extensions to the graph reading group tomorrow!

New reading group recording on YouTube: youtu.be/02I7EtgIQec Nikos Karalias presents his paper "Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions"! You can join the reading group yourself here: m2d2.io/talks/log2/abo…

I'll be presenting our work on optimal approximation algorithms for combinatorial problems with graph neural nets at the Mathematics of Modern Machine Learning (M3L) workshop. Saturday 4pm, room 242! Arxiv: arxiv.org/abs/2310.00526

Accepted at NeurIPS 2024 as a spotlight :) We'll post an updated version on Arxiv next week!

Mr. President, Ukraine did not “start” this war. Russia launched an unprovoked and brutal invasion claiming hundreds of thousands of lives. The Road to Peace must be built on the Truth.🇺🇸🇺🇦 “Russia Invades Ukraine in Largest European Attack Since WWII” Fox News (February 24,

It’s not advisable to vote for someone who tells you they will do something in the hope that they are lying to you and won’t do it.

🔥 New workshop at NeurIPS Conference! DiffCoALG bridges the gap between classic algorithms & differentiable learning. Think: LLM reasoning, routing, SAT, MIP — neurally optimized end-to-end. 📌 Submit by Aug 22! 🔗 sites.google.com/view/diffcoalg… #NeurIPS2025

Join DiffCoALG NeurIPS Conference 2025 — a workshop on neural methods + classic algorithms (think: TSP, SAT, MIP, and more). 🧠 Theory meets practice. The deadline is only 3 days away! 📆 Submit by Aug 22 🔗 sites.google.com/view/diffcoalg…

We have extended the deadline :)