activity
20242026
collaborators

8 papers

math.GM2026

Counting Connected and Disconnected Ways to Assemble a Jigsaw Puzzle

Prarthana Agrawal, Abdurrahman Hadi Erturk, Ard A. Louis

A jigsaw puzzle may be assembled in many different ways. Some assembly sequences remain connected throughout, while others temporarily build separate parts of the puzzle before joi…

math.CO2026

Successive vertex orderings of graphs

Prarthana Agrawal, Abdurrahman Hadi Erturk, Ard A. Louis

A successive vertex ordering of a graph is a linear ordering of its vertices in which every vertex except the first has at least one neighbour appearing earlier. Such orderings ari…

stat.ML2026

Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement

Yoonsoo Nam, Nayara Fonseca, Seok Hyeong Lee +6

Dynamic feature transformation (the rich regime) does not always align with predictive performance (better representation), yet accuracy is often used as a proxy for richness, limi…

cs.LG2026

Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks

Ouns El Harzli, Yoonsoo Nam, Ilja Kuzborskij +2

Algorithmic stability is a classical framework for analyzing the generalization error of learning algorithms. It predicts that an algorithm has small generalization error if it is…

cs.LG2025

A simple mean field model of feature learning

Niclas Göring, Chris Mingard, Yoonsoo Nam +1

Feature learning (FL), where neural networks adapt their internal representations during training, remains poorly understood. Using methods from statistical physics, we derive a tr…

cs.LG2025

Feature learning is decoupled from generalization in high capacity neural networks

Niclas Alexander Göring, Charles London, Abdurrahman Hadi Erturk +3

Neural networks outperform kernel methods, sometimes by orders of magnitude, e.g. on staircase functions. This advantage stems from the ability of neural networks to learn features…