22 citations · 47 across the 35 of their papers we have counts for
42 papers
Finite Probes Suffice: Identifiability and Universality for Weight-Space Learning
Soutrik Sarangi, Yonatan Sverdlov, Adir Dayan +2
Learning properties of neural networks has recently attracted growing interest, with existing approaches operating either directly on network parameters or through probe-based repr…
Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
Snir Hordan, Nadav Dym, Tim Seppelt
Graphs with a simple spectrum admit cubic-time isomorphism testing, yet we prove that for every natural number , the -Weisfeiler-Leman (-WL) test cannot distinguish all no…
When and How to Canonize: A Generalization Perspective
Yonatan Sverdlov, Benjamin Friedman, Snir Hordan +1
While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canonization to non-invar…
Transport, Don't Generate: Deterministic Geometric Flows for Combinatorial Optimization
Benjy Friedmann, Nadav Dym
Recent advances in Neural Combinatorial Optimization (NCO) have been dominated by diffusion models that treat the Euclidean Traveling Salesman Problem (TSP) as a stochastic $N \tim…
Quantitative Approximation Rates for Group Equivariant Learning
Jonathan W. Siegel, Snir Hordan, Hannah Lawrence +2
The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitat…
Short-Range Oversquashing
Yaaqov Mishayev, Yonatan Sverdlov, Tal Amir +1
Message Passing Neural Networks (MPNNs) are widely used for learning on graphs, but their ability to process long-range information is limited by the phenomenon of oversquashing. T…