2 citations · 5 across the 10 of their papers we have counts for
5 papers · 1 filter
Transformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes
Khashayar Gatmiry, Nathan W. Henry, Chloe H. Su +5
We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depending on their initialization.…
Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization
Robert Jankowski, Pedro Almagro-Blanco, Marián Boguñá +2
Graph neural networks (GNNs) can operate on large graphs but become infrastructure-sensitive at the scale of millions of nodes and typically require scalable training techniques fo…
Powers of the Vandermonde determinant are eventually non-SNP
Thien Le, Melanie Weber
We prove a conjecture of Monical, Tokcan, and Yong that every fixed positive power of the Vandermonde determinant is non-SNP in all sufficiently many variables, where a polynomial…
Contrastive Neural Algorithmic Reasoning for Graph Coloring
Thien Le, Tianyu Zhao, Melanie Weber
Graph coloring seeks to assigns colors to a graph's nodes so that adjacent nodes receive different colors, using as few colors as possible. Here, we study approximate -coloring,…
Towards Distillation Guarantees under Algorithmic Alignment for Combinatorial Optimization
Thien Le, Melanie Weber
Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowl…