English
Related papers

Related papers: A Systematic Empirical Study of Grokking: Depth, A…

200 papers

We present a simple neural network that can learn modular arithmetic tasks and exhibits a sudden jump in generalization known as ``grokking''. Concretely, we present (i) fully-connected two-layer networks that exhibit grokking on various…

Machine Learning · Computer Science 2023-01-10 Andrey Gromov

Grokking is a intriguing phenomenon in machine learning where a neural network, after many training iterations with negligible improvement in generalization, suddenly achieves high accuracy on unseen data. By working in the quantum-inspired…

Spectral bias, the tendency of neural networks to learn low frequencies first, can be both a blessing and a curse. While it enhances the generalization capabilities by suppressing high-frequency noise, it can be a limitation in scientific…

Machine Learning · Computer Science 2026-05-08 Shuai Jiang , Alexey Voronin , Eric Cyr , Ben Southworth

Transformers trained on modular arithmetic exhibit sharp transitions between memorization, generalization, and collapse. We show that weight decay acts as a scalar empirical control parameter for these regimes, and introduce two cheap…

Machine Learning · Computer Science 2026-05-21 Lucky Verma

We discuss two solvable grokking (generalisation beyond overfitting) models in a rule learning scenario. We show that grokking is a phase transition and find exact analytic expressions for the critical exponents, grokking probability, and…

Statistical Mechanics · Physics 2022-10-28 Bojan Žunkovič , Enej Ilievski

Training dynamics during grokking concentrate along a small number of dominant update directions -- the spectral edge -- which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability…

Machine Learning · Computer Science 2026-04-09 Yongzhong Xu

Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural…

Computation and Language · Computer Science 2025-05-08 Roman Abramov , Felix Steinbauer , Gjergji Kasneci

Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs), however, challenge this view: We show that removing…

Machine Learning · Computer Science 2019-06-03 Aditya Golatkar , Alessandro Achille , Stefano Soatto

Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memorization occurs in a deep network, we use a recently developed…

Machine Learning · Computer Science 2021-06-01 Cory Stephenson , Suchismita Padhy , Abhinav Ganesh , Yue Hui , Hanlin Tang , SueYeon Chung

A key property of deep neural networks (DNNs) is their ability to learn new features during training. This intriguing aspect of deep learning stands out most clearly in recently reported Grokking phenomena. While mainly reflected as a…

Machine Learning · Statistics 2024-05-07 Noa Rubin , Inbar Seroussi , Zohar Ringel

Neural networks trained to solve modular arithmetic tasks exhibit grokking, a phenomenon where the test accuracy starts improving long after the model achieves 100% training accuracy in the training process. It is often taken as an example…

We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation…

Computation and Language · Computer Science 2025-02-07 Ang Lv , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Rui Yan

Grokking is the phenomenon where neural networks NNs initially fit the training data and later generalize to the test data during training. In this paper, we empirically provide a frequency perspective to explain the emergence of this…

Machine Learning · Computer Science 2024-05-29 Zhangchen Zhou , Yaoyu Zhang , Zhi-Qin John Xu

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

The grokking phenomenon as reported by Power et al. ( arXiv:2201.02177 ) refers to a regime where a long period of overfitting is followed by a seemingly sudden transition to perfect generalization. In this paper, we attempt to reveal the…

Machine Learning · Computer Science 2022-06-14 Vimal Thilak , Etai Littwin , Shuangfei Zhai , Omid Saremi , Roni Paiss , Joshua Susskind

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 training accuracy…

Machine Learning · Computer Science 2026-04-21 Ping Wang

Large language models have demonstrated remarkable capabilities across many tasks, yet face significant challenges when dealing with recursive reasoning problems, those requiring the resolution of nested hierarchical structures. While prior…

Artificial Intelligence · Computer Science 2025-12-03 Zhiyuan He

Dropout is a widely-used regularization technique, often required to obtain state-of-the-art for a number of architectures. This work demonstrates that dropout introduces two distinct but entangled regularization effects: an explicit effect…

Machine Learning · Computer Science 2020-10-16 Colin Wei , Sham Kakade , Tengyu Ma

The study of Deep Network (DN) training dynamics has largely focused on the evolution of the loss function, evaluated on or around train and test set data points. In fact, many DN phenomenon were first introduced in literature with that…

Machine Learning · Computer Science 2023-10-23 Ahmed Imtiaz Humayun , Randall Balestriero , Richard Baraniuk

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect…

Machine Learning · Computer Science 2023-02-13 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Volkan Cevher
‹ Prev 1 3 4 5 6 7 10 Next ›