English
Related papers

Related papers: Explaining Grokking and Information Bottleneck thr…

200 papers

Modern deep neural networks have achieved impressive performance on tasks from image classification to natural language processing. Surprisingly, these complex systems with massive amounts of parameters exhibit the same structural…

Machine Learning · Computer Science 2023-06-21 Hien Dang , Tho Tran , Stanley Osher , Hung Tran-The , Nhat Ho , Tan Nguyen

Neural Collapse (NC) gives a precise description of the representations of classes in the final hidden layer of classification neural networks. This description provides insights into how these networks learn features and generalize well…

Machine Learning · Computer Science 2023-08-08 Liam Parker , Emre Onal , Anton Stengel , Jake Intrater

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Machine Learning · Computer Science 2026-05-20 Zhipeng Zhang

In this paper, we introduce matrix entropy as an analytical tool for studying supervised learning, investigating the information content of data representations and classification head vectors, as well as the dynamic interactions between…

Machine Learning · Computer Science 2025-03-03 Kun Song , Zhiquan Tan , Bochao Zou , Jiansheng Chen , Huimin Ma , Weiran Huang

Over the past decade, deep neural networks have proven to be adept in image classification tasks, often surpassing humans in terms of accuracy. However, standard neural networks often fail to understand the concept of hierarchical…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Amitangshu Mukherjee , Isha Garg , Kaushik Roy

A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network parameters. Such non-trivial…

Machine Learning · Computer Science 2021-12-07 Mohammad Pezeshki , Amartya Mitra , Yoshua Bengio , Guillaume Lajoie

Grokking describes a delayed generalization phenomenon in which a neural network achieves perfect training accuracy long before validation accuracy improves, followed by an abrupt transition to strong generalization. Existing detection…

Machine Learning · Computer Science 2026-04-24 Shreel Golwala

To improve how neural networks function it is crucial to understand their learning process. The information bottleneck theory of deep learning proposes that neural networks achieve good generalization by compressing their representations to…

Machine Learning · Computer Science 2023-04-03 Ivan Chelombiev , Conor Houghton , Cian O'Donnell

Despite the popularity and success of deep learning, there is limited understanding of when, how, and why neural networks generalize to unseen examples. Since learning can be seen as extracting information from data, we formally study…

Machine Learning · Computer Science 2023-06-29 Hrayr Harutyunyan

Improvement and adoption of generative machine learning models is rapidly accelerating, as exemplified by the popularity of LLMs (Large Language Models) for text, and diffusion models for image generation. As generative models become…

Machine Learning · Computer Science 2024-08-30 Matteo Marchi , Stefano Soatto , Pratik Chaudhari , Paulo Tabuada

The inference of causal relationships using observational data from partially observed multivariate systems with hidden variables is a fundamental question in many scientific domains. Methods extracting causal information from conditional…

Machine Learning · Statistics 2020-10-13 Daniel Chicharro , Michel Besserve , Stefano Panzeri

The information bottleneck principle is an elegant and useful approach to representation learning. In this paper, we investigate the problem of representation learning in the context of reinforcement learning using the information…

Machine Learning · Computer Science 2019-11-14 Pei Yingjun , Hou Xinwen

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this…

Machine Learning · Computer Science 2024-03-01 Clare Lyle , Zeyu Zheng , Khimya Khetarpal , Hado van Hasselt , Razvan Pascanu , James Martens , Will Dabney

Neural collapse ($\mathcal{NC}$) is a phenomenon observed in classification tasks where top-layer representations collapse into their class means, which become equinorm, equiangular and aligned with the classifiers. These behaviours --…

Machine Learning · Computer Science 2024-11-27 Robert Wu , Vardan Papyan

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of…

Machine Learning · Computer Science 2023-05-23 Peter Súkeník , Marco Mondelli , Christoph Lampert

Extracting relevant information from data is crucial for all forms of learning. The information bottleneck (IB) method formalizes this, offering a mathematically precise and conceptually appealing framework for understanding learning…

Machine Learning · Computer Science 2021-10-27 Vudtiwat Ngampruetikorn , David J. Schwab

Unlike primates, training artificial neural networks on changing data distributions leads to a rapid decrease in performance on old tasks. This phenomenon is commonly referred to as catastrophic forgetting. In this paper, we investigate the…

Machine Learning · Computer Science 2023-10-10 Daniel Anthes , Sushrut Thorat , Peter König , Tim C. Kietzmann

The training dynamics and generalization properties of neural networks (NN) can be precisely characterized in function space via the neural tangent kernel (NTK). Structural changes to the NTK during training reflect feature learning and…

Machine Learning · Statistics 2022-02-11 Haozhe Shan , Blake Bordelon

What happens when generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models? Some prior work warns of "model collapse" as the web is overwhelmed by synthetic data; other work…

Machine Learning · Computer Science 2025-03-19 Joshua Kazdan , Rylan Schaeffer , Apratim Dey , Matthias Gerstgrasser , Rafael Rafailov , David L. Donoho , Sanmi Koyejo
‹ Prev 1 8 9 10 Next ›