English
Related papers

Related papers: Preventing Model Collapse Under Overparametrizatio…

200 papers

Neural multivariate regression underpins a wide range of domains, including control, robotics, and finance, yet the geometry of its learned representations remains poorly characterized. While neural collapse has been shown to benefit…

Machine Learning · Computer Science 2026-05-11 George Andriopoulos , Zixuan Dong , Bimarsha Adhikari , Keith Ross

Class imbalance in real-world data poses a common bottleneck for machine learning tasks, since achieving good generalization on under-represented examples is often challenging. Mitigation strategies, such as under or oversampling the data…

Disordered Systems and Neural Networks · Physics 2025-02-03 Emanuele Loffredo , Mauro Pastore , Simona Cocco , Rémi Monasson

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other…

Machine Learning · Computer Science 2025-09-30 George Andriopoulos , Zixuan Dong , Li Guo , Zifan Zhao , Keith Ross

We develop and analyze a principled approach to kernel ridge regression under covariate shift. The goal is to learn a regression function with small mean squared error over a target distribution, based on unlabeled data from there and…

Methodology · Statistics 2025-07-25 Kaizheng Wang

The Ridgeless minimum $\ell_2$-norm interpolator in overparametrized linear regression has attracted considerable attention in recent years in both machine learning and statistics communities. While it seems to defy conventional wisdom that…

Statistics Theory · Mathematics 2026-01-21 Qiyang Han , Xiaocong Xu

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct…

Machine Learning · Computer Science 2021-08-30 Elad Levi , Tete Xiao , Xiaolong Wang , Trevor Darrell

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across…

Computation and Language · Computer Science 2025-09-03 Daniele Gambetta , Gizem Gezici , Fosca Giannotti , Dino Pedreschi , Alistair Knott , Luca Pappalardo

The proliferation of generative artificial intelligence has given rise to an interactive learning environment, where model parameters are continuously updated using not only data generated by natural processes, but also synthetic outputs…

Machine Learning · Computer Science 2026-05-20 Yuchen Wu , Kangjie Zhou , Weijie Su

Dropout Regularization, serving to reduce variance, is nearly ubiquitous in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks configured with random…

Machine Learning · Computer Science 2021-08-30 Christopher Sun , Jai Sharma , Milind Maiti

Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We…

Machine Learning · Statistics 2021-06-08 Zhu Li , Zhi-Hua Zhou , Arthur Gretton

Recently, deep neural networks have been found to nearly interpolate training data but still generalize well in various applications. To help understand such a phenomenon, it has been of interest to analyze the ridge estimator and its…

Statistics Theory · Mathematics 2024-05-03 Libin Liang , Zhiqiang Tan

High dimensional error covariance matrices and their inverses are used to weight the contribution of observation and background information in data assimilation procedures. As observation error covariance matrices are often obtained by…

Optimization and Control · Mathematics 2019-10-02 Jemima M. Tabeart , Sarah L. Dance , Amos S. Lawless , Nancy K. Nichols , Joanne A. Waller

Existing theory suggests that for linear regression problems categorized by capacity and source conditions, gradient descent (GD) is always minimax optimal, while both ridge regression and online stochastic gradient descent (SGD) are…

Machine Learning · Statistics 2025-09-23 Jingfeng Wu , Peter L. Bartlett , Jason D. Lee , Sham M. Kakade , Bin Yu

In recent years, model collapse has become a critical issue in language model training, making it essential to understand the underlying mechanisms driving this phenomenon. In this paper, we investigate recursive parametric model training…

Machine Learning · Statistics 2025-05-23 Shirong Xu , Hengzhi He , Guang Cheng

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

A common way to avoid overfitting in supervised learning is early stopping, where a held-out set is used for iterative evaluation during training to find a sweet spot in the number of training steps that gives maximum generalization.…

Machine Learning · Computer Science 2022-08-23 Ali Vardasbi , Maarten de Rijke , Mostafa Dehghani

Recent successes of massively overparameterized models have inspired a new line of work investigating the underlying conditions that enable overparameterized models to generalize well. This paper considers a framework where the possibly…

Machine Learning · Computer Science 2023-12-06 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

Training models on uncurated Text Embeddings (TEs) derived from raw tabular data can lead to a severe failure mode known as model collapse, where predictions converge to a single class regardless of input. By comparing models trained with…

Machine Learning · Computer Science 2025-06-24 Lucas Mattioli , Youness Ait Hadichou , Sabrina Chaouche , Martin Gonzalez

We provide a statistical analysis of regularization-based continual learning on a sequence of linear regression tasks, with emphasis on how different regularization terms affect the model performance. We first derive the convergence rate…

Machine Learning · Computer Science 2024-06-11 Xuyang Zhao , Huiyuan Wang , Weiran Huang , Wei Lin

Self-supervised representation learning is central to modern machine learning because it extracts structured latent features from unlabeled data and enables robust transfer across tasks and domains. However, it can suffer from…

Disordered Systems and Neural Networks · Physics 2026-04-14 Louie Hong Yao , Yuhao Li , Shengchao Liu