English
Related papers

Related papers: Risk Phase Transitions in Spiked Regression: Align…

200 papers

One of the major open problems in machine learning is to characterize generalization in the overparameterized regime, where most traditional generalization bounds become inconsistent even for overparameterized linear regression. In many…

Machine Learning · Computer Science 2023-11-22 Jing Xu , Jiaye Teng , Yang Yuan , Andrew Chi-Chih Yao

This work studies finite-sample properties of the risk of the minimum-norm interpolating predictor in high-dimensional regression models. If the effective rank of the covariance matrix $\Sigma$ of the $p$ regression features is much larger…

Machine Learning · Statistics 2021-03-23 Florentina Bunea , Seth Strimas-Mackey , Marten Wegkamp

A regression model with more parameters than data points in the training data is overparametrized and has the capability to interpolate the training data. Based on the classical bias-variance tradeoff expressions, it is commonly assumed…

Machine Learning · Computer Science 2023-04-18 Tomas McKelvey

Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that are stable across sites and discard unstable features.…

Machine Learning · Computer Science 2024-09-11 Minh Nguyen , Alan Q. Wang , Heejong Kim , Mert R. Sabuncu

In high-dimensional principal component analysis, important inferential targets include both leading spikes and the associated principal eigenspaces. Such problems arise naturally in high-dimensional factor models, where leading principal…

Statistics Theory · Mathematics 2026-03-26 Yanqing Yin , Wang Zhou

One classical canon of statistics is that large models are prone to overfitting, and model selection procedures are necessary for high dimensional data. However, many overparameterized models, such as neural networks, perform very well in…

Machine Learning · Statistics 2021-01-05 Xi Chen , Qiang Liu , Xin T. Tong

The effects of spike timing precision and dynamical behavior on error correction in spiking neurons were investigated. Stationary discharges -- phase locked, quasiperiodic, or chaotic -- were induced in a simulated neuron by presenting…

Neurons and Cognition · Quantitative Biology 2007-05-23 Michael Stiber

The paradigm of weak-to-strong generalization constitutes the training of a strong AI model on data labeled by a weak AI model, with the goal that the strong model nevertheless outperforms its weak supervisor on the target task of interest.…

Machine Learning · Computer Science 2025-02-05 Abhijeet Mulgund , Chirag Pabbaraju

Clinical risk prediction is a valuable tool for guiding healthcare interventions toward those most likely to benefit. Yet, evaluating the pairing of a risk prediction model with an intervention using randomized controlled trials presents…

Methodology · Statistics 2025-10-31 Valerie Odeh-Couvertier , Gabriel Zayas-Caban , Brian Patterson , Amy Cochran

We study the asymptotic behavior of the spectrum of a random matrix where a non-linearity is applied entry-wise to a Wigner matrix perturbed by a rank-one spike with independent and identically distributed entries. In this setting, we show…

Probability · Mathematics 2023-10-24 Alice Guionnet , Justin Ko , Florent Krzakala , Pierre Mergny , Lenka Zdeborová

We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE), with linear regression models. As the development of machine learning for causal inference, a wide range of large-scale models for…

Econometrics · Economics 2022-02-17 Masahiro Kato , Masaaki Imaizumi

We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data. In particular, we consider simple…

Machine Learning · Statistics 2022-06-17 Chen Cheng , John Duchi , Rohith Kuditipudi

The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to…

Image and Video Processing · Electrical Eng. & Systems 2021-04-27 Max-Heinrich Laves , Sontje Ihler , Jacob F. Fast , Lüder A. Kahrs , Tobias Ortmaier

Modern machine learning systems such as deep neural networks are often highly over-parameterized so that they can fit the noisy training data exactly, yet they can still achieve small test errors in practice. In this paper, we study this…

Machine Learning · Computer Science 2022-01-04 Yuan Cao , Quanquan Gu , Mikhail Belkin

I argue that regularizing terms in standard regression methods not only help against overfitting finite data, but sometimes also yield better causal models in the infinite sample regime. I first consider a multi-dimensional variable…

Machine Learning · Statistics 2019-07-01 Dominik Janzing

Large language models often achieve strong benchmark gains without corresponding improvements in broader capability. We hypothesize that this discrepancy arises from differences in training regimes induced by data distribution. To…

Machine Learning · Computer Science 2026-04-10 Hongjian Zou , Yidan Wang , Qi Ding , Yixuan Liao , Xiaoxin Chen

Spurious correlations, unstable statistical shortcuts a model can exploit, are expected to degrade performance out-of-distribution (OOD). However, across many popular OOD generalization benchmarks, vanilla empirical risk minimization (ERM)…

Machine Learning · Computer Science 2025-08-05 Olawale Salaudeen , Nicole Chiou , Shiny Weng , Sanmi Koyejo

Although randomized controlled trials have long been regarded as the ``gold standard'' for evaluating treatment effects, there is no natural prevention from post-treatment events. For example, non-compliance makes the actual treatment…

Methodology · Statistics 2025-04-25 Qinqing Liu , Xiang Peng , Tao Zhang , Yuhao Deng

We study the cost of overfitting in noisy kernel ridge regression (KRR), which we define as the ratio between the test error of the interpolating ridgeless model and the test error of the optimally-tuned model. We take an "agnostic" view in…

Machine Learning · Statistics 2024-03-25 Lijia Zhou , James B. Simon , Gal Vardi , Nathan Srebro

We develop a collection of methods for adjusting the predictions of quantile regression to ensure coverage. Our methods are model agnostic and can be used to correct for high-dimensional overfitting bias with only minimal assumptions.…

Methodology · Statistics 2025-11-10 Isaac Gibbs , John J. Cherian , Emmanuel J. Candès
‹ Prev 1 4 5 6 7 8 10 Next ›