Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Garg, Anvit, Bhattacharya, Sohom, Sur, Pragya
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Statistics Theory Methodology
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Generalization error of min-norm interpolators in transfer learning
di: Song, Yanke, et al.
Pubblicazione: (2024)

Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling
di: Li, Yufan, et al.
Pubblicazione: (2025)

Spectrum-Aware Debiasing: A Modern Inference Framework with Applications to Principal Components Regression
di: Li, Yufan, et al.
Pubblicazione: (2023)

Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
di: Lecoiu, Radu, et al.
Pubblicazione: (2026)

Predictive Inference in Multi-environment Scenarios
di: Duchi, John C., et al.
Pubblicazione: (2024)

Optimal and Structure-Adaptive CATE Estimation with Kernel Ridge Regression
di: Kim, Seok-Jin
Pubblicazione: (2026)

Characterizing Finite-Dimensional Posterior Marginals in High-Dimensional GLMs via Leave-One-Out
di: Sáenz, Manuel, et al.
Pubblicazione: (2025)

Understanding Overparametrization in Survival Models through Interpolation
di: Liu, Yin, et al.
Pubblicazione: (2025)

Riesz Regression As Direct Density Ratio Estimation
di: Kato, Masahiro
Pubblicazione: (2025)

A Kernel-Based Conditional Two-Sample Test Using Nearest Neighbors (with Applications to Calibration, Regression Curves, and Simulation-Based Inference)
di: Chatterjee, Anirban, et al.
Pubblicazione: (2024)

HEDE: Heritability estimation in high dimensions by Ensembling Debiased Estimators
di: Song, Yanke, et al.
Pubblicazione: (2024)

Nearest Neighbor Matching as Least Squares Density Ratio Estimation and Riesz Regression
di: Kato, Masahiro
Pubblicazione: (2025)

On Quantification of Borrowing of Information in Hierarchical Bayesian Models
di: Ghosh, Prasenjit, et al.
Pubblicazione: (2025)

Algebraic and Statistical Properties of the Ordinary Least Squares Interpolator
di: Shen, Dennis, et al.
Pubblicazione: (2023)

Transfer Learning for High-dimensional Quantile Regression with Distribution Shift
di: Bai, Ruiqi, et al.
Pubblicazione: (2024)

Boosting the Power of Kernel Two-Sample Tests
di: Chatterjee, Anirban, et al.
Pubblicazione: (2023)

Hierarchical Bayesian Operator-induced Symbolic Regression Trees for Structural Learning of Scientific Expressions
di: Roy, Somjit, et al.
Pubblicazione: (2025)

Lasso Penalization for High-Dimensional Beta Regression Models: Computation, Analysis, and Inference
di: Ramezani, Niloofar, et al.
Pubblicazione: (2025)

AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression
di: He, Zelin, et al.
Pubblicazione: (2024)

Adaptive finite element type decomposition of Gaussian processes
di: Kim, Jaehoan, et al.
Pubblicazione: (2025)

Statistical Inference for Gradient Boosting Regression
di: Fang, Haimo, et al.
Pubblicazione: (2025)

Bayesian Semi-supervised Inference via a Debiased Modeling Approach
di: Sert, Gözde, et al.
Pubblicazione: (2025)

Bayesian Models for Joint Selection of Features and Auto-Regressive Lags: Theory and Applications in Environmental and Financial Forecasting
di: Manna, Alokesh, et al.
Pubblicazione: (2025)

Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning
di: Shen, Ye, et al.
Pubblicazione: (2021)

How to Measure Evidence and Its Strength: Bayes Factors or Relative Belief Ratios?
di: Al-Labadi, Luai, et al.
Pubblicazione: (2023)

Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification
di: Leiner, James, et al.
Pubblicazione: (2025)

Optimal Discriminant Analysis in High-Dimensional Latent Factor Models
di: Bing, Xin, et al.
Pubblicazione: (2022)

Inferring Change Points in Regression via Sample Weighting
di: Arpino, Gabriel, et al.
Pubblicazione: (2026)

Finite-Sample Inference for Sparsely Permuted Linear Regression
di: Ota, Hirofumi, et al.
Pubblicazione: (2026)

Targeted Data Fusion for Region-Specific Survival Effects in the AMP HIV Prevention Trials
di: Liu, Yi, et al.
Pubblicazione: (2025)

Double Cross-fit Doubly Robust Estimators: Beyond Series Regression
di: McClean, Alec, et al.
Pubblicazione: (2024)

Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
di: Tan, Kai, et al.
Pubblicazione: (2024)

Transfer Learning for Classification under Decision Rule Drift with Application to Optimal Individualized Treatment Rule Estimation
di: Wang, Xiaohan, et al.
Pubblicazione: (2025)

Optimal Demixing of Nonparametric Densities
di: Fan, Jianqing, et al.
Pubblicazione: (2026)

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
di: Liang, Tengyuan, et al.
Pubblicazione: (2022)

genriesz: A Python Package for Automatic Debiased Machine Learning with Generalized Riesz Regression
di: Kato, Masahiro
Pubblicazione: (2026)

Covariate Balancing and Riesz Regression Should Be Guided by the Neyman Orthogonal Score in Debiased Machine Learning
di: Kato, Masahiro
Pubblicazione: (2026)

Collapsing Categories for Regression with Mixed Predictors
di: Song, Chaegeun, et al.
Pubblicazione: (2025)

Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions
di: Bing, Simon, et al.
Pubblicazione: (2023)

Adaptive Split Balancing for Optimal Random Forest
di: Zhang, Yuqian, et al.
Pubblicazione: (2024)