Yu He
@dransyhe.bsky.social
CS PhD student @Stanford | BA+MEng @Cambridge
dransyhe.github.io
dransyhe.github.io
[3/n]
We align GNNs with primal-dual algorithms via a bipartite representation between primal/dual variables, and theoretically prove it retains performance guarantees 📊📚
We align GNNs with primal-dual algorithms via a bipartite representation between primal/dual variables, and theoretically prove it retains performance guarantees 📊📚
July 13, 2025 at 9:35 PM
[3/n]
We align GNNs with primal-dual algorithms via a bipartite representation between primal/dual variables, and theoretically prove it retains performance guarantees 📊📚
We align GNNs with primal-dual algorithms via a bipartite representation between primal/dual variables, and theoretically prove it retains performance guarantees 📊📚
[2/n]
PDNAR is a general NAR framework for NP-hard problems, built on the primal-dual approximation paradigm—a powerful tool in both exact and approximate algorithm design 🔧📐
PDNAR is a general NAR framework for NP-hard problems, built on the primal-dual approximation paradigm—a powerful tool in both exact and approximate algorithm design 🔧📐
July 13, 2025 at 9:34 PM
[2/n]
PDNAR is a general NAR framework for NP-hard problems, built on the primal-dual approximation paradigm—a powerful tool in both exact and approximate algorithm design 🔧📐
PDNAR is a general NAR framework for NP-hard problems, built on the primal-dual approximation paradigm—a powerful tool in both exact and approximate algorithm design 🔧📐
[1/n]
What is NAR?
It trains neural networks to simulate algorithmic executions, imbuing them with structured, algorithmic thinking on real-world data 🧮🤖
But... most NAR work focuses on polynomial-time problems.
❗️Real-world problems like facility location are NP-hard!
What is NAR?
It trains neural networks to simulate algorithmic executions, imbuing them with structured, algorithmic thinking on real-world data 🧮🤖
But... most NAR work focuses on polynomial-time problems.
❗️Real-world problems like facility location are NP-hard!
July 13, 2025 at 9:34 PM
[1/n]
What is NAR?
It trains neural networks to simulate algorithmic executions, imbuing them with structured, algorithmic thinking on real-world data 🧮🤖
But... most NAR work focuses on polynomial-time problems.
❗️Real-world problems like facility location are NP-hard!
What is NAR?
It trains neural networks to simulate algorithmic executions, imbuing them with structured, algorithmic thinking on real-world data 🧮🤖
But... most NAR work focuses on polynomial-time problems.
❗️Real-world problems like facility location are NP-hard!
Our ✨spotlight paper✨ "Primal-Dual Neural Algorithmic Reasoning" is coming to #ICML2025!
We bring Neural Algorithmic Reasoning (NAR) to the NP-hard frontier 💥
🗓 Poster session: Tuesday 11:00–13:30
📍 East Exhibition Hall A-B, # E-3003
🔗 openreview.net/pdf?id=iBpkz...
🧵
We bring Neural Algorithmic Reasoning (NAR) to the NP-hard frontier 💥
🗓 Poster session: Tuesday 11:00–13:30
📍 East Exhibition Hall A-B, # E-3003
🔗 openreview.net/pdf?id=iBpkz...
🧵
July 13, 2025 at 9:34 PM
Our ✨spotlight paper✨ "Primal-Dual Neural Algorithmic Reasoning" is coming to #ICML2025!
We bring Neural Algorithmic Reasoning (NAR) to the NP-hard frontier 💥
🗓 Poster session: Tuesday 11:00–13:30
📍 East Exhibition Hall A-B, # E-3003
🔗 openreview.net/pdf?id=iBpkz...
🧵
We bring Neural Algorithmic Reasoning (NAR) to the NP-hard frontier 💥
🗓 Poster session: Tuesday 11:00–13:30
📍 East Exhibition Hall A-B, # E-3003
🔗 openreview.net/pdf?id=iBpkz...
🧵