5 papers
Lean-GAP: A Dataset of Formalized Graduate Algebra Problems
Seewoo Lee, Byung-Hak Hwang, Hyojae Lim +10
We present Lean-GAP (Lean-Graduate Agebra Problems), 430 formalized graduate-level algebra problems from the textbook Abstract Algebra by Dummit and Foote. We develop a scalable pi…
Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
Hyeonbin Hwang, Yeachan Park
Grokking, the sudden transition from memorization to generalization, is characterized by the emergence of low-dimensional representations, yet the mechanism underlying this organiz…
Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)
Yoonsoo Nam, Seok Hyeong Lee, Clementine C J Domine +5
In physics, complex systems are often simplified into minimal, solvable models that retain only the core principles. In machine learning, layerwise linear models (e.g., linear neur…
Absence of Closed-Form Descriptions for Gradient Flow in Two-Layer Narrow Networks
Yeachan Park
In the field of machine learning, comprehending the intricate training dynamics of neural networks poses a significant challenge. This paper explores the training dynamics of neura…
Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation
Yeachan Park, Minseok Kim, Yeoneung Kim
We propose novel methodologies aimed at accelerating the grokking phenomenon, which refers to the rapid increment of test accuracy after a long period of overfitting as reported in…