English
Related papers

Related papers: Model Capacity Determines Grokking through Competi…

200 papers

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

Human explanations of natural language, rationales, form a tool to assess whether models learn a label for the right reasons or rely on dataset-specific shortcuts. Sufficiency is a common metric for estimating the informativeness of…

Computation and Language · Computer Science 2025-11-21 Jonathan Kamp , Lisa Beinborn , Antske Fokkens

Very large deep learning models trained using gradient descent are remarkably resistant to memorization given their huge capacity, but are at the same time capable of fitting large datasets of pure noise. Here methods are introduced by…

Machine Learning · Computer Science 2022-12-22 Benjamin L. Badger

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Machine Learning · Computer Science 2025-12-29 Lianghe Shi , Meng Wu , Huijie Zhang , Zekai Zhang , Molei Tao , Qing Qu

Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs'…

Computation and Language · Computer Science 2025-03-05 Chulin Xie , Yangsibo Huang , Chiyuan Zhang , Da Yu , Xinyun Chen , Bill Yuchen Lin , Bo Li , Badih Ghazi , Ravi Kumar

Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective. We analyze the distinctions between memorization and generalization in diffusion models…

Machine Learning · Computer Science 2026-02-12 Zekai Zhang , Xiao Li , Xiang Li , Lianghe Shi , Meng Wu , Molei Tao , Qing Qu

Despite their success in image generation, diffusion models can memorize training data, raising serious privacy and copyright concerns. Although prior work has sought to characterize, detect, and mitigate memorization, the fundamental…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Juyeop Kim , Songkuk Kim , Jong-Seok Lee

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

This paper demonstrates that grokking behavior in modular arithmetic with a modulus P in a neural network can be controlled by modifying the profile of the activation function as well as the depth and width of the model. Plotting the even…

Machine Learning · Computer Science 2024-11-11 Ahmed Salah , David Yevick

Recent work by Power et al. (2022) highlighted a surprising "grokking" phenomenon in learning arithmetic tasks: a neural net first "memorizes" the training set, resulting in perfect training accuracy but near-random test accuracy, and after…

Machine Learning · Computer Science 2024-04-03 Kaifeng Lyu , Jikai Jin , Zhiyuan Li , Simon S. Du , Jason D. Lee , Wei Hu

Large pretrained self-attention neural networks, or transformers, have been very successful in various tasks recently. The performance of a model on a given task depends on its ability to memorize and generalize the training data. Large…

Machine Learning · Computer Science 2024-08-01 Aki Härmä , Marcin Pietrasik , Anna Wilbik

Critical-data-size accounts of grokking suggest a natural post-threshold intuition: once training data is sufficient to identify the underlying rule, additional data should accelerate validation convergence. We show that this intuition can…

Machine Learning · Computer Science 2026-05-15 Shin So , Kyelim Lee , Albert No

Memorization in large language models poses critical risks for privacy and fairness as these systems scale to billions of parameters. While previous studies established correlations between memorization and factors like token frequency and…

Machine Learning · Computer Science 2025-09-01 Jie Zhang , Qinghua Zhao , Chi-ho Lin , Zhongfeng Kang , Lei Li

The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of…

Software Engineering · Computer Science 2024-01-15 Zhou Yang , Zhipeng Zhao , Chenyu Wang , Jieke Shi , Dongsun Kim , DongGyun Han , David Lo

We attribute grokking, the phenomenon where generalization is much delayed after memorization, to compression. To do so, we define linear mapping number (LMN) to measure network complexity, which is a generalized version of linear region…

Machine Learning · Computer Science 2023-10-10 Ziming Liu , Ziqian Zhong , Max Tegmark

Standard optimization theories struggle to explain grokking, where generalization occurs long after training convergence. While geometric studies attribute this to slow drift, they often overlook the interaction between the optimizer's…

Machine Learning · Computer Science 2026-03-17 Pratyush Acharya , Habish Dhakal

We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representative reasoning types, composition and comparison, we…

Computation and Language · Computer Science 2024-11-01 Boshi Wang , Xiang Yue , Yu Su , Huan Sun

Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In…

Machine Learning · Computer Science 2021-01-19 Sumukh Aithal K , Dhruva Kashyap , Natarajan Subramanyam

Due to their capacity to generate novel and high-quality samples, diffusion models have attracted significant research interest in recent years. Notably, the typical training objective of diffusion models, i.e., denoising score matching,…

Machine Learning · Computer Science 2025-02-21 Xiangming Gu , Chao Du , Tianyu Pang , Chongxuan Li , Min Lin , Ye Wang

Large Language Models (LLMs) are typically trained on data mixtures: most data come from web scrapes, while a small portion is curated from high-quality sources with dense domain-specific knowledge. In this paper, we show that when training…

Machine Learning · Computer Science 2026-05-12 Xinran Gu , Kaifeng Lyu , Jiazheng Li , Jingzhao Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›