English
Related papers

Related papers: Grokking modular arithmetic

200 papers

It has been observed that the input space of deep neural network classifiers can exhibit `fragmentation', where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the…

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al.,…

Machine Learning · Statistics 2024-09-06 Hugo Cui , Luca Pesce , Yatin Dandi , Florent Krzakala , Yue M. Lu , Lenka Zdeborová , Bruno Loureiro

In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixtures. While previous research has extensively analyzed this…

Machine Learning · Statistics 2025-05-20 Samet Demir , Zafer Dogan

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

Understanding how deep neural networks learn representations remains a central challenge in machine learning theory. In this work, we propose a feature-centric framework for analyzing neural network training by relating weight updates to…

Machine Learning · Computer Science 2026-05-08 Taehun Cha , Daniel Beaglehole , Adityanarayanan Radhakrishnan , Donghun Lee

The crux of graph classification lies in the effective representation learning for the entire graph. Typical graph neural networks focus on modeling the local dependencies when aggregating features of neighboring nodes, and obtain the…

Machine Learning · Computer Science 2024-01-02 Wenjie Pei , Weina Xu , Zongze Wu , Weichao Li , Jinfan Wang , Guangming Lu , Xiangrong Wang

Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a…

Machine Learning · Statistics 2019-06-21 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Neural networks have succeeded in many reasoning tasks. Empirically, these tasks require specialized network structures, e.g., Graph Neural Networks (GNNs) perform well on many such tasks, but less structured networks fail. Theoretically,…

Machine Learning · Computer Science 2020-02-18 Keyulu Xu , Jingling Li , Mozhi Zhang , Simon S. Du , Ken-ichi Kawarabayashi , Stefanie Jegelka

Understanding the internal representations learned by neural networks is a cornerstone challenge in the science of machine learning. While there have been significant recent strides in some cases towards understanding how neural networks…

Machine Learning · Computer Science 2024-02-20 Depen Morwani , Benjamin L. Edelman , Costin-Andrei Oncescu , Rosie Zhao , Sham Kakade

The mechanisms by which modularity emerges in complex networks are not well understood but recent reports have suggested that modularity may arise from evolutionary selection. We show that finding the modularity of a network is analogous to…

Disordered Systems and Neural Networks · Physics 2009-11-10 Roger Guimera , Marta Sales-Pardo , Luis A. N. Amaral

Natural target functions and tasks typically exhibit hierarchical modularity -- they can be broken down into simpler sub-functions that are organized in a hierarchy. Such sub-functions have two important features: they have a distinct set…

Machine Learning · Computer Science 2023-10-31 Shreyas Malakarjun Patil , Loizos Michael , Constantine Dovrolis

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

A recent breakthrough in deep learning theory shows that the training of over-parameterized deep neural networks can be characterized by a kernel function called \textit{neural tangent kernel} (NTK). However, it is known that this type of…

Machine Learning · Computer Science 2020-10-07 Zixiang Chen , Yuan Cao , Quanquan Gu , Tong Zhang

We study gradient-based regularization methods for neural networks. We mainly focus on two regularization methods: the total variation and the Tikhonov regularization. Applying these methods is equivalent to using neural networks to solve…

Machine Learning · Computer Science 2022-11-09 Lingfeng Li , Xue-Cheng Tai , Jiang Yang

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions…

Machine Learning · Computer Science 2024-06-19 Chenxiao Yang , Qitian Wu , David Wipf , Ruoyu Sun , Junchi Yan

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

Recent studies have revealed that neural networks learn interpretable algorithms for many simple problems. However, little is known about how these algorithms emerge during training. In this article, I study the training dynamics of a small…

Machine Learning · Computer Science 2024-10-29 Tiberiu Musat

This paper considers the Pointer Value Retrieval (PVR) benchmark introduced in [ZRKB21], where a 'reasoning' function acts on a string of digits to produce the label. More generally, the paper considers the learning of logical functions…

Machine Learning · Computer Science 2022-10-21 Emmanuel Abbe , Samy Bengio , Elisabetta Cornacchia , Jon Kleinberg , Aryo Lotfi , Maithra Raghu , Chiyuan Zhang

Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we…

Machine Learning · Computer Science 2026-04-16 Laura Gomezjurado Gonzalez

The learned weights of a neural network are often considered devoid of scrutable internal structure. To discern structure in these weights, we introduce a measurable notion of modularity for multi-layer perceptrons (MLPs), and investigate…

Neural and Evolutionary Computing · Computer Science 2022-02-09 Daniel Filan , Shlomi Hod , Cody Wild , Andrew Critch , Stuart Russell
‹ Prev 1 4 5 6 7 8 10 Next ›