English
Related papers

Related papers: Preventing Model Collapse Under Overparametrizatio…

200 papers

Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic data will fundamentally reshape the web data ecosystem.…

Computation and Language · Computer Science 2025-05-29 Xuekai Zhu , Daixuan Cheng , Hengli Li , Kaiyan Zhang , Ermo Hua , Xingtai Lv , Ning Ding , Zhouhan Lin , Zilong Zheng , Bowen Zhou

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

Two-phase sampling designs are frequently employed in epidemiological studies and large-scale health surveys. In such designs, certain variables are exclusively collected within a second-phase random subsample of the initial first-phase…

Methodology · Statistics 2024-03-25 Lingxiao Wang

The notion of neural collapse refers to several emergent phenomena that have been empirically observed across various canonical classification problems. During the terminal phase of training a deep neural network, the feature embedding of…

Machine Learning · Computer Science 2023-04-05 Duc Anh Nguyen , Ron Levie , Julian Lienen , Gitta Kutyniok , Eyke Hüllermeier

Standard conformal anomaly detection provides marginal finite-sample guarantees under the assumption of exchangeability . However, real-world data often exhibit distribution shifts, necessitating a weighted conformal approach to adapt to…

Machine Learning · Statistics 2026-03-25 Oliver Hennhöfer , Christine Preisach

Ridge regression with random coefficients provides an important alternative to fixed coefficients regression in high dimensional setting when the effects are expected to be small but not zeros. This paper considers estimation and prediction…

Machine Learning · Statistics 2023-06-29 Hongzhe Zhang , Hongzhe Li

Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approximate the performance of individual fine-tuned models for…

Machine Learning · Computer Science 2025-10-17 Mohammadsajad Alipour , Mohammad Mohammadi Amiri

Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. Although recent model merging methods have shown promising results, they struggle to maintain…

Machine Learning · Computer Science 2025-06-04 Zijing Wang , Xingle Xu , Yongkang Liu , Yiqun Zhang , Peiqin Lin , Shi Feng , Xiaocui Yang , Daling Wang , Hinrich Schütze

Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods. One efficient strategy to deal with this problem is to employ resampling techniques before…

Machine Learning · Computer Science 2021-05-18 Bin Liu , Grigorios Tsoumakas

Upweighting high-quality data in LLM pretraining often improves performance, but in datalimited regimes, especially under overtraining, stronger upweighting increases repetition and can degrade performance. However, standard scaling laws do…

Computation and Language · Computer Science 2026-05-05 Fengze Liu , Weidong Zhou , Binbin Liu , Ping Guo , Zijun Wang , Bingni Zhang , Yifan Zhang , Yifeng Yu , Xiaohuan Zhou , Taifeng Wang

We consider $L^2$-regularized linear (ridge) regression over a finite data sample $X$ with bounded covariance and linear prediction targets $y$ with additive isotropic noise of finite variance. We present an iterative procedure to compute…

Machine Learning · Computer Science 2026-05-28 Jack Timmermans , Sergio A. Alvarez

As modern machine learning models continue to advance the computational frontier, it has become increasingly important to develop precise estimates for expected performance improvements under different model and data scaling regimes.…

Machine Learning · Computer Science 2023-06-13 Lechao Xiao , Hong Hu , Theodor Misiakiewicz , Yue M. Lu , Jeffrey Pennington

This study demonstrates that double descent can be mitigated by adding a dropout layer adjacent to the fully connected linear layer. The unexpected double-descent phenomenon garnered substantial attention in recent years, resulting in…

Machine Learning · Computer Science 2025-08-08 Tian-Le Yang , Joe Suzuki

A prominent self-supervised learning paradigm is to model the representations as clusters, or more generally as a mixture model. Learning to map the data samples to compact representations and fitting the mixture model simultaneously leads…

Machine Learning · Computer Science 2024-10-21 Hariprasath Govindarajan , Per Sidén , Jacob Roll , Fredrik Lindsten

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Machine Learning · Statistics 2020-11-09 Ben Adlam , Jeffrey Pennington

We consider fully row/column-correlated linear regression models and study several classical estimators (including minimum norm interpolators (GLS), ordinary least squares (LS), and ridge regressors). We show that \emph{Random Duality…

Machine Learning · Statistics 2024-06-14 Mihailo Stojnic

Dropout as regularization has been used extensively to prevent overfitting for training neural networks. During training, units and their connections are randomly dropped, which could be considered as sampling many different submodels from…

Machine Learning · Computer Science 2022-04-28 Zhaoyuan Yang , Arpit Jain

Subsampling is a popular approach to alleviating the computational burden for analyzing massive datasets. Recent efforts have been devoted to various statistical models without explicit regularization. In this paper, we develop an efficient…

Methodology · Statistics 2022-04-12 Yunlu Chen , Nan Zhang

Modern regression problems often involve high-dimensional data and a careful tuning of the regularization hyperparameters is crucial to avoid overly complex models that may overfit the training data while guaranteeing desirable properties…

Machine Learning · Computer Science 2026-04-08 Maria-Florina Balcan , Saumya Goyal , Dravyansh Sharma

In statistics and machine learning, when we train a fitted model on available data, we typically want to ensure that we are searching within a model class that contains at least one accurate model -- that is, we would like to ensure an…

Statistics Theory · Mathematics 2025-06-06 Manuel M. Müller , Yuetian Luo , Rina Foygel Barber