paper-with-me

Papers

Grokking as a Falsifiable Finite-Size Transition

2026-03-25 · Yuda Bi, Chenyu Zhang, Qiheng Wang, Vince D Calhoun arxiv

Grokking -- the delayed onset of generalization after early memorization -- is often described with phase-transition language, but that claim has lacked falsifiable finite-size inputs. Here we supply those inputs by treating the group order $p$ of $\mathbb{Z}_p$ as an admissible extensive variable and a held-out spectral head-tail contrast as a representation-level order parameter, then apply a condensed-matter-style diagnostic chain to coarse-grid sweeps and a dense near-critical addition audit. Binder-like crossings reveal a shared finite-size boundary, and susceptibility comparison strongly disfavors a smooth-crossover interpretation ($Δ\mathrm{AIC}=16.8$ in the near-critical audit). Phase-transition language in grokking can therefore be tested as a quantitative finite-size claim rather than invoked as analogy alone, although the transition order remains unresolved at present.

📄 PDF Abstract BibTeX arXiv:2603.24746

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Grokking as Dimensional Phase Transition in Neural Networks

2026-04-06 · Ping Wang arxiv

Neural network grokking -- the abrupt memorization-to-generalization transition -- challenges our understanding of learning dynamics. Through finite-size scaling of gradient avalanche dynamics across eight model scales, …

Dimensional Criticality at Grokking Across MLPs and Transformers

2026-04-06 · Ping Wang arxiv

Abrupt transitions between distinct dynamical regimes are a hallmark of complex systems. Grokking in deep neural networks provides a striking example -- an abrupt transition from memorization to generalization long after…

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization

2026-03-05 · Truong Xuan Khanh, Truong Quynh Hoa, Luu Duc Trung, Phan Thanh Duc arxiv

Grokking -- the sudden generalisation that appears long after a model has perfectly memorised its training data -- has been widely observed but lacks a quantitative theory explaining the length of the delay. We show that…

Critical Data Size of Language Models from a Grokking Perspective

2024-01-19 · Xuekai Zhu, Yao Fu, BoWen Zhou, Zhouhan Lin

We explore the critical data size in language models, a threshold that marks a fundamental shift from quick memorization to slow generalization. We formalize the phase transition under the grokking configuration into the…

Language ModelingLanguage ModellingMemorization

Emergence via Phase Transitions: Mechanism Landscapes and Universal Convergence Across Complex Systems

2026-05-25 · Truong Xuan Khanh arxiv

Across machine learning, biology, and physics, independently evolving systems often converge toward strikingly similar high-level structures despite radically different microscopic details. Grokking circuits converge acr…