The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
From MaRDI portal
(Redirected from Publication:5072044)
Recommendations
- A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
- Triple descent and the two kinds of overfitting: where and why do they appear?*
- Surprises in high-dimensional ridgeless least squares interpolation
- Two models of double descent for weak features
- Generalisation error in learning with random features and the hidden manifold model*
Cited in
(81)- A duality framework for analyzing random feature and two-layer neural networks
- On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions
- A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks
- The interpolation phase transition in neural networks: memorization and generalization under lazy training
- Stability of the scattering transform for deformations with minimal regularity
- Inference on time series nonparametric conditional moment restrictions using nonlinear sieves
- The generalization error of max-margin linear classifiers: benign overfitting and high dimensional asymptotics in the overparametrized regime
- A new central limit theorem for the augmented IPW estimator: variance inflation, cross-fit covariance and beyond
- Observable adjustments in single-index models for regularized M-estimators with bounded p/n
- A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
- On the robustness of the minimim _2 interpolator
- Representation and regression problems in neural networks: relaxation, generalization, and numerics
- A Unifying Tutorial on Approximate Message Passing
- Empirical risk minimization in the interpolating regime with application to neural network learning
- Per-example gradient regularization improves learning signals from noisy data
- High-Dimensional Analysis of Double Descent for Linear Regression with Random Projections
- Quantitative CLTs in deep neural networks
- Ensemble linear interpolators: the role of ensembling
- The common intuition to transfer learning can win or lose: case studies for linear regression
- Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
- Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation
- Theoretical issues in deep networks
- For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability
- Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
- Random features and polynomial rules
- A universal law of robustness via isoperimetry
- Kronecker-product random matrices and a matrix least squares problem
- Learning curves for deep structured Gaussian feature models
- Deterministic equivalent and error universality of deep random features learning
- Overparameterization and generalization error: weighted trigonometric interpolation
- The inverse variance-flatness relation in stochastic gradient descent is critical for finding flat minima
- Fluctuations, bias, variance and ensemble of learners: exact asymptotics for convex losses in high-dimension
- Precise learning curves and higher-order scaling limits for dot-product kernel regression
- Redundant representations help generalization in wide neural networks
- The dynamics of representation learning in shallow, non-linear autoencoders
- Universality of regularized regression estimators in high dimensions
- Six lectures on linearized neural networks
- On the benefit of width for neural networks: disappearance of basins
- Benign Overfitting and Noisy Features
- Large-dimensional random matrix theory and its applications in deep learning and wireless communications
- Analysis of high-dimensional Gaussian labeled-unlabeled mixture model via message-passing algorithm
- Differentially private learning beyond the classical dimensionality regime
- Bayes-optimal learning of deep random networks of extensive-width
- High-dimensional asymptotics of VAEs: threshold of posterior collapse and dataset-size dependence of rate-distortion curve
- Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks
- Precise statistical analysis of classification accuracies for adversarial training
- Asymptotic generalization error in the online learning of linearized two-layer neural networks
- A simple probabilistic neural network for machine understanding
- High dimensional binary classification under label shift: phase transition and regularization
- scientific article; zbMATH DE number 7626737 (Why is no real title available?)
- Dyson equation for correlated linearizations and test error of random features regression
- A primer on Bayesian neural networks: review and debates
- Synchronizing pretrained kernel regressors with applications to American option pricing
- A geometrical analysis of kernel ridge regression and its applications
- Solving partial differential equations with random feature models
- Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks
- Conditioning of random Fourier feature matrices: double descent and generalization error
- Double data piling: a high-dimensional solution for asymptotically perfect multi-category classification
- Robust kernel-based gradient descent with random features
- A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors
- A dynamic view of some anomalous phenomena in SGD for over-parametrized neural networks
- Homogenization of SGD in high-dimensions: exact dynamics and generalization properties
- The generalization error of random features regression: Precise asymptotics and double descent curve
- Free dynamics of feature learning processes
- Conservative SPDEs as fluctuating mean field limits of stochastic gradient descent
- Deep networks for system identification: a survey
- Deep learning: a statistical viewpoint
- scientific article; zbMATH DE number 7625163 (Why is no real title available?)
- Feature learning and generalization error analysis of two-layer linear neural networks for high-dimensional inputs
- SketchySGD: reliable stochastic optimization via randomized curvature estimates
- How more data can hurt: instability and regularization in next-generation reservoir computing
- Mathematical methods in quantum chemistry. Abstracts from the workshop held March 9--14, 2025
- The high-dimensional asymptotics of principal component regression
- An equivalence principle for the spectrum of random inner-product kernel matrices with polynomial scalings
- Neural networks trained with SGD learn distributions of increasing complexity^*
- High-dimensional learning of narrow neural networks
- Universality of approximate message passing with semirandom matrices
- On the robustness of minimum norm interpolators and regularized empirical risk minimizers
- The curse of overparametrization in adversarial training: precise analysis of robust generalization for random features regression
- AdaBoost and robust one-bit compressed sensing
- A precise high-dimensional asymptotic theory for boosting and minimum-\(\ell_1\)-norm interpolated classifiers
This page was built for publication: The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5072044)
