On the public citation graph

Just interpolate: Kernel “Ridgeless” regression can generalize

0 signed · 121 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.

Claim with ORCID

Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.

See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1007/11503415_20openalex-snapshot

Exponential Convergence Rates in Classification

inferredcites →https://doi.org/10.1007/3-540-44581-1_15openalex-snapshot

Rademacher and Gaussian Complexities: Risk Bounds and Structural Results

inferredcites →https://doi.org/10.1007/978-3-642-41136-6_11openalex-snapshot

Kernel Ridge Regression

inferredcites →https://doi.org/10.1007/b97848openalex-snapshot

A Distribution-Free Theory of Nonparametric Regression

inferredcites →https://doi.org/10.1007/bf00353874openalex-snapshot

On the limit of the largest eigenvalue of the large dimensional sample covariance matrix

inferredcites →https://doi.org/10.1007/bf00889887openalex-snapshot

The origins of kriging

inferredcites →https://doi.org/10.1007/s00365-006-0663-2openalex-snapshot

On Early Stopping in Gradient Descent Learning

inferredcites →https://doi.org/10.1007/s10208-004-0134-1openalex-snapshot

Model Selection for Regularized Least-Squares Algorithm in Learning Theory

inferredcites →https://doi.org/10.1007/s10208-006-0196-8openalex-snapshot

Optimal Rates for the Regularized Least-Squares Algorithm

inferredcites →https://doi.org/10.1007/s102080010030openalex-snapshot

Best Choices for Regularization Parameters in Learning Theory: On the Bias—Variance Problem

inferredcites →https://doi.org/10.1017/cbo9780511809682openalex-snapshot

Kernel Methods for Pattern Analysis

inferredcites →https://doi.org/10.1023/a:1018946025316openalex-snapshot

Regularization Networks and Support Vector Machines

inferredcites →https://doi.org/10.1080/00401706.1979.10489751openalex-snapshot

Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter

inferredcites →https://doi.org/10.1080/01621459.2020.1745812openalex-snapshot

Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits

inferredcites →https://doi.org/10.1109/ita.2018.8503198openalex-snapshot

Implicit Regularization in Matrix Factorization

inferredcites →https://doi.org/10.1137/1.9781611970128openalex-snapshot

Spline Models for Observational Data

inferredcites →https://doi.org/10.1214/08-aos648openalex-snapshot

The spectrum of kernel random matrices

inferredcites →https://doi.org/10.48550/arxiv.1201.0490openalex-snapshot

Scikit-learn: Machine Learning in Python

inferredcites →https://doi.org/10.48550/arxiv.1412.6614openalex-snapshot

In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning

inferredcites →https://doi.org/10.48550/arxiv.1611.03530openalex-snapshot

Understanding deep learning requires rethinking generalization

inferredcites →https://doi.org/10.48550/arxiv.1801.03437openalex-snapshot

Approximation beats concentration? An approximation view on inference with smooth radial kernels

inferredcites →https://doi.org/10.48550/arxiv.1802.01396openalex-snapshot

To understand deep learning we need to understand kernel learning

inferredcites →https://doi.org/10.48550/arxiv.1806.05161openalex-snapshot

Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.2139/ssrn.4609871openalex-extracted

Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control

inferred← citeshttps://doi.org/10.1002/cpa.22008openalex-snapshot

The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve

inferred← citeshttps://doi.org/10.1007/978-3-030-86523-8_6openalex-snapshot

Which Minimizer Does My Neural Network Converge To?

inferred← citeshttps://doi.org/10.1007/978-3-030-95860-2_6openalex-snapshot

Regularization in Reproducing Kernel Hilbert Spaces

inferred← citeshttps://doi.org/10.1007/978-3-030-95860-2_8openalex-snapshot

Regularization for Nonlinear System Identification

inferred← citeshttps://doi.org/10.1007/978-981-16-8233-9_9openalex-snapshot

Reflecting on the Role of Overparameterization: Is it Solely Harmful?

inferred← citeshttps://doi.org/10.1007/978-981-95-8110-8_4openalex-snapshot

Scaling Laws of Deep-Learning Neural Networks: Taxonomy and Survey

inferred← citeshttps://doi.org/10.1007/s00440-023-01248-yopenalex-snapshot

Tractability from overparametrization: the example of the negative perceptron

inferred← citeshttps://doi.org/10.1007/s00440-024-01278-0openalex-snapshot

Benign overfitting and adaptive nonparametric regression

inferred← citeshttps://doi.org/10.1007/s00440-024-01336-7openalex-snapshot

A geometrical viewpoint on the benign overfitting property of the minimum $$\ell _2$$-norm interpolant estimator and its universality

inferred← citeshttps://doi.org/10.1007/s10589-026-00776-2openalex-snapshot

Effectively leveraging momentum terms in stochastic line search frameworks for fast optimization of finite-sum problems

inferred← citeshttps://doi.org/10.1007/s10994-022-06265-xopenalex-snapshot

SVRG meets AdaGrad: painless variance reduction

inferred← citeshttps://doi.org/10.1007/s10994-024-06692-yopenalex-snapshot

Knoop: practical enhancement of knockoff with over-parameterization for variable selection

inferred← citeshttps://doi.org/10.1007/s42952-025-00352-0openalex-snapshot

Overparametrized linear regression with noisy and missing data

inferred← citeshttps://doi.org/10.1007/s43670-022-00022-wopenalex-snapshot

Learning from non-random data in Hilbert spaces: an optimal recovery perspective

inferred← citeshttps://doi.org/10.1007/s43670-023-00063-9openalex-snapshot

HARFE: hard-ridge random feature expansion

inferred← citeshttps://doi.org/10.1007/s43670-023-00075-5openalex-snapshot

Rates of convergence for regression with the graph poly-Laplacian

inferred← citeshttps://doi.org/10.1016/j.acha.2021.12.003openalex-snapshot

Generalization error of random feature and kernel methods: Hypercontractivity and kernel matrix concentration

inferred← citeshttps://doi.org/10.1016/j.acha.2026.101920openalex-snapshot

Generalization error curves for analytic spectral algorithms under power-law decay

inferred← citeshttps://doi.org/10.1016/j.automatica.2024.111907openalex-snapshot

Deep networks for system identification: A survey

inferred← citeshttps://doi.org/10.1016/j.cmpb.2022.106905openalex-snapshot

Kernel machine learning methods to handle missing responses with complex predictors. Application in modelling five-year glucose changes using distributional representations

inferred← citeshttps://doi.org/10.1016/j.cnsns.2025.109343openalex-snapshot

Solving partial differential equations with random feature models

inferred← citeshttps://doi.org/10.1016/j.csda.2020.107154openalex-snapshot

Communication-efficient distributed estimator for generalized linear models with a diverging number of covariates

inferred← citeshttps://doi.org/10.1016/j.jece.2026.123930openalex-snapshot

Prediction toxicity threshold of herbicides single and combine to submerged plants: A QSAR model with ridge regression

inferred← citeshttps://doi.org/10.1016/j.jfranklin.2024.107311openalex-snapshot

Polynomial-based kernel reproduced gradient descent for stochastic optimization

inferred← citeshttps://doi.org/10.1016/j.neucom.2023.126227openalex-snapshot

Do we really need a new theory to understand over-parameterization?

inferred← citeshttps://doi.org/10.1016/j.neunet.2024.107110openalex-snapshot

Convergence analysis of deep Ritz method with over-parameterization

inferred← citeshttps://doi.org/10.1016/j.physletb.2026.140722openalex-snapshot

Using neural networks to accelerate TALYS-2.0 nuclear reaction simulations

inferred← citeshttps://doi.org/10.1016/j.sigpro.2025.109904openalex-snapshot

Softmax-kernel reproduced gradient descent for stochastic optimization on streaming data

inferred← citeshttps://doi.org/10.1016/j.slads.2026.100026openalex-snapshot

Towards a statistical understanding of neural networks: Beyond the neural tangent kernel theories

inferred← citeshttps://doi.org/10.1016/j.xinn.2026.101427openalex-snapshot

Research Fronts 2025: Mapping the evolving landscape of global science and technology

inferred← citeshttps://doi.org/10.1017/s0962492921000027openalex-snapshot

Deep learning: a statistical viewpoint

inferred← citeshttps://doi.org/10.1017/s0962492921000039openalex-snapshot

Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation

inferred← citeshttps://doi.org/10.1038/s41467-020-14663-9openalex-snapshot

Complexity control by gradient descent in deep networks

inferred← citeshttps://doi.org/10.1038/s41467-021-23103-1openalex-snapshot

Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks

inferred← citeshttps://doi.org/10.1038/s42256-021-00345-8openalex-snapshot

Fitting elephants in modern machine learning by statistically consistent interpolation

inferred← citeshttps://doi.org/10.1073/pnas.2103091118openalex-snapshot

Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training

inferred← citeshttps://doi.org/10.1073/pnas.2310002121openalex-snapshot

The training process of many deep networks explores the same low-dimensional manifold

inferred← citeshttps://doi.org/10.1080/01621459.2020.1745812openalex-snapshot

Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits

inferred← citeshttps://doi.org/10.1080/01621459.2020.1844210openalex-snapshot

A Multi-resolution Theory for Approximating Infinite-p-Zero-n: Transitional Inference, Individualized Predictions, and a World Without Bias-Variance Tradeoff

inferred← citeshttps://doi.org/10.1080/01621459.2020.1853547openalex-snapshot

Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks

inferred← citeshttps://doi.org/10.1080/01621459.2022.2093206openalex-snapshot

Benign Overfitting and Noisy Features

inferred← citeshttps://doi.org/10.1080/01621459.2024.2368844openalex-snapshot

Enhanced Response Envelope via Envelope Regularization

inferred← citeshttps://doi.org/10.1080/02331934.2025.2551250openalex-snapshot

Convergence conditions for stochastic line search based optimization of over-parametrized models

inferred← citeshttps://doi.org/10.1088/1742-5468/ac3a77openalex-snapshot

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*

inferred← citeshttps://doi.org/10.1088/1742-5468/ac98a9openalex-snapshot

On the proliferation of support vectors in high dimensions*

inferred← citeshttps://doi.org/10.1088/1742-5468/ad292aopenalex-snapshot

Six lectures on linearized neural networks

inferred← citeshttps://doi.org/10.1088/1742-5468/ad642aopenalex-snapshot

Learning curves for deep structured Gaussian feature models*

inferred← citeshttps://doi.org/10.1093/biomet/asac049openalex-snapshot

Kernel two-sample tests in high dimensions: interplay between moment discrepancy and dimension-and-sample orders

inferred← citeshttps://doi.org/10.1093/biomet/asad048openalex-snapshot

Kernel interpolation generalizes poorly

inferred← citeshttps://doi.org/10.1093/biomet/asae057openalex-snapshot

The phase diagram of kernel interpolation in large dimensions

inferred← citeshttps://doi.org/10.1093/imaiai/iaad054openalex-snapshot

Conditioning of random Fourier feature matrices: double descent and generalization error

inferred← citeshttps://doi.org/10.1101/2023.12.09.570922openalex-snapshot

AI without networks

inferred← citeshttps://doi.org/10.1103/physreve.106.025304openalex-snapshot

Bias-variance decomposition of overparameterized regression with random linear features

inferred← citeshttps://doi.org/10.1103/physrevresearch.4.013201openalex-snapshot

Memorizing without overfitting: Bias, variance, and interpolation in overparameterized models

inferred← citeshttps://doi.org/10.1103/physrevresearch.7.023119openalex-snapshot

Thermodynamic limit in learning period three

inferred← citeshttps://doi.org/10.1109/ieeeconf53345.2021.9723382openalex-snapshot

Model selection and explainability in neural networks using a polytope interpolation framework

inferred← citeshttps://doi.org/10.1109/isit50566.2022.9834388openalex-snapshot

The Directional Bias Helps Stochastic Gradient Descent to Generalize in Kernel Regression Models

inferred← citeshttps://doi.org/10.1109/isit50566.2022.9834569openalex-snapshot

Regularization-wise double descent: Why it occurs and how to eliminate it

inferred← citeshttps://doi.org/10.1109/tit.2022.3215088openalex-snapshot

On Generalization Bounds for Deep Networks Based on Loss Surface Implicit Regularization

inferred← citeshttps://doi.org/10.1109/tit.2023.3344656openalex-snapshot

Optimal Rates for Agnostic Distributed Learning

inferred← citeshttps://doi.org/10.1109/tit.2025.3531048openalex-snapshot

Generalization Performance of Empirical Risk Minimization on Over-Parameterized Deep ReLU Nets

inferred← citeshttps://doi.org/10.1109/tkde.2023.3270750openalex-snapshot

COLTR: Semi-Supervised Learning to Rank With Co-Training and Over-Parameterization for Web Search

inferred← citeshttps://doi.org/10.1109/tpami.2021.3120183openalex-snapshot

Towards a Unified Quadrature Framework for Large-Scale Kernel Machines

inferred← citeshttps://doi.org/10.1109/tsp.2025.3549591openalex-snapshot

Online Federated Reproduced Gradient Descent With Time-Varying Global Optima

inferred← citeshttps://doi.org/10.1111/rssb.12542openalex-snapshot

Universal Prediction Band via Semi-Definite Programming

inferred← citeshttps://doi.org/10.1137/20m1320031openalex-snapshot

Diversity Sampling is an Implicit Regularization for Kernel Methods

inferred← citeshttps://doi.org/10.1137/22m1499819openalex-snapshot

On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions

inferred← citeshttps://doi.org/10.1137/22m1519948openalex-snapshot

Kernel Interpolation of High Dimensional Scattered Data

inferred← citeshttps://doi.org/10.1137/22m1540302openalex-snapshot

A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors

inferred← citeshttps://doi.org/10.1137/23m1568764openalex-snapshot

New Equivalences between Interpolation and SVMs: Kernels and Structured Features

inferred← citeshttps://doi.org/10.1137/24m1642548openalex-snapshot

Ensemble Linear Interpolators: The Role of Ensembling

inferred← citeshttps://doi.org/10.1142/s0219530522400115openalex-snapshot

For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability

inferred← citeshttps://doi.org/10.1142/s0219530526500028openalex-snapshot

Sobolev norm inconsistency of kernel interpolation

inferred← citeshttps://doi.org/10.1214/20-aos1990openalex-snapshot

Linearized two-layers neural networks in high dimension

inferred← citeshttps://doi.org/10.1214/21-aos2116openalex-snapshot

Canonical thresholding for nonsparse high-dimensional linear regression

inferred← citeshttps://doi.org/10.1214/21-aos2133openalex-snapshot

Surprises in high-dimensional ridgeless least squares interpolation

inferred← citeshttps://doi.org/10.1214/22-aos2170openalex-snapshot

A precise high-dimensional asymptotic theory for boosting and minimum-ℓ1-norm interpolated classifiers

inferred← citeshttps://doi.org/10.1214/22-aos2190openalex-snapshot

On the robustness of minimum norm interpolators and regularized empirical risk minimizers

inferred← citeshttps://doi.org/10.1214/22-aos2211openalex-snapshot

The interpolation phase transition in neural networks: Memorization and generalization under lazy training

inferred← citeshttps://doi.org/10.1214/22-aos2212openalex-snapshot

A sieve stochastic gradient descent estimator for online nonparametric regression in Sobolev ellipsoids

inferred← citeshttps://doi.org/10.1214/23-aap2010openalex-snapshot

Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks

inferred← citeshttps://doi.org/10.1214/25-aos2489openalex-snapshot

The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime

inferred← citeshttps://doi.org/10.1214/25-aos2532openalex-snapshot

The high-dimensional asymptotics of principal component regression

inferred← citeshttps://doi.org/10.12677/pm.2026.165133openalex-snapshot

Large Adaptive Implicit Regularization and GeneralizationAnalysis for Multi-Kernel Interpolation

inferred← citeshttps://doi.org/10.1561/2200000092openalex-snapshot

A Unifying Tutorial on Approximate Message Passing

inferred← citeshttps://doi.org/10.2139/ssrn.5032413openalex-snapshot

"Double Descent" in Portfolio Optimization: Dance between Theoretical Sharpe Ratio and Estimation Accuracy

inferred← citeshttps://doi.org/10.23919/acc63710.2025.11107619openalex-snapshot

Safe and High-Performance Learning of Model Predictive Control using Kernel-Based Interpolation

inferred← citeshttps://doi.org/10.23939/sisn2026.19.100openalex-snapshot

Study of Regression Model Optimization by Means of Regularization

inferred← citeshttps://doi.org/10.3150/22-bej1473openalex-snapshot

On the robustness of the minimim ℓ2 interpolator

inferred← citeshttps://doi.org/10.3150/25-bej1877openalex-snapshot

Benign overfitting in time-series linear models with over-parameterization

inferred← citeshttps://doi.org/10.3390/math10060993openalex-snapshot

Statistical Methods with Applications in Data Mining: A Review of the Most Recent Works

inferred← citeshttps://doi.org/10.4208/cicp.oa-2023-0101openalex-snapshot

Convergence Analysis of PINNs with Over-Parameterization

inferred← citeshttps://doi.org/10.4208/cicp.oa-2023-0264openalex-snapshot

Convergence Analysis for Over-Parameterized Deep Learning

inferred← citeshttps://doi.org/10.4208/cicp.oa-2025-0102openalex-snapshot

A Complete Error Analysis of PINNs for Elliptic Equations Using Projected Stochastic Gradient Descent

inferred← citeshttps://doi.org/10.70675/24f761cbz67f0z4760zbeb2z340aaddb0a57openalex-snapshot

Topics in high-dimensional and non-parametric inference

inferred← citeshttps://doi.org/10.70675/c6ef8709z9816z43aeza681zd89f9145e79eopenalex-snapshot

When Random Forests Meet Neural Networks : A Finite-Sample Analysis

inferred← citeshttps://doi.org/10.70675/ffef887ez4944z4cb3z82b9zcaa0294ed85aopenalex-snapshot

Contributions to structured high-dimensional inference

Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.