English
Related papers

Related papers: Explaining grokking through circuit efficiency

200 papers

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry

Grokking, the abrupt transition from memorization to generalisation after extended training, suggests the presence of competing solution basins with distinct statistical properties. We study this phenomenon through the lens of Singular…

Machine Learning · Statistics 2026-05-08 Ben Cullen , Sergio Estan-Ruiz , Riya Danait , Jiayi Li

Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

Why do neural networks trained with large learning rates for a longer time often lead to better generalization? In this paper, we delve into this question by examining the relation between training and testing loss in neural networks.…

Machine Learning · Computer Science 2024-01-23 Yinuo Ren , Chao Ma , Lexing Ying

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 Data Efficiency…

Computation and Language · Computer Science 2024-05-24 Xuekai Zhu , Yao Fu , Bowen Zhou , Zhouhan Lin

Grokking -- the abrupt transition from memorization to generalization long after near-zero training loss -- has been studied mainly in single-task settings. We extend geometric analysis to multi-task modular arithmetic, training…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks,…

Machine Learning · Computer Science 2026-02-02 Christiaan P. Opperman , Anna S. Bosman , Katherine M. Malan

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize…

We propose that learning in deep neural networks proceeds in two phases: a rapid curve fitting phase followed by a slower compression or coarse graining phase. This view is supported by the shared temporal structure of three phenomena:…

High Energy Physics - Theory · Physics 2025-07-28 Robert de Mello Koch , Animik Ghosh

For humans, language production and comprehension is sensitive to the hierarchical structure of sentences. In natural language processing, past work has questioned how effectively neural sequence models like transformers capture this…

Computation and Language · Computer Science 2023-05-31 Shikhar Murty , Pratyusha Sharma , Jacob Andreas , Christopher D. Manning

\emph{Memorization} in neural networks lacks a precise operational definition and is often inferred from the grokking regime, where training accuracy saturates while test accuracy remains very low. We identify a previously unreported third…

Machine Learning · Computer Science 2026-02-04 Hari K Prakash , Charles H Martin

Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Agus Gunawan , Xu Yin , Kang Zhang

Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm minimization, feature emergence, or the late discovery of sparse subnetworks. These…

Machine Learning · Computer Science 2026-05-18 Kai Hidajat , Solden Stoll , Joseph An

We present a non-asymptotic theory of generalization in deep learning where the empirical neural tangent kernel partitions the output space. In directions corresponding to signal, error dissipates rapidly; in the vast orthogonal dimensions…

Machine Learning · Computer Science 2026-05-05 Elon Litman , Gabe Guo

Grokking -- the abrupt transition from memorization to generalization after prolonged training -- has been linked to confinement on low-dimensional execution manifolds in modular arithmetic. Whether this mechanism extends beyond arithmetic…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Jinjin Gu , Xianzheng Ma , Xiangtao Kong , Yu Qiao , Chao Dong

Highly over-parameterized models can simultaneously memorize noisy labels and generalize well, yet how these behaviors coexist remains poorly understood. In this work, we investigate the underlying mechanisms of this coexistence using…

Machine Learning · Computer Science 2026-05-19 Linyu Liu , Pinyan Lu

Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources…

Machine Learning · Computer Science 2022-10-25 Oyebade K. Oyedotun , Konstantinos Papadopoulos , Djamila Aouada

While the phenomenon of grokking, i.e., delayed generalization, has been studied extensively, it remains an open problem whether there is a mathematical framework that characterizes what kind of features will emerge, how and in which…

Machine Learning · Computer Science 2025-12-03 Yuandong Tian
‹ Prev 1 3 4 5 6 7 10 Next ›