On early stopping in gradient descent learning
From MaRDI portal
Publication:2642922
Stopping times; optimal stopping problems; gambling theory (60G40) Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Stochastic approximation (62L20) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)
Recommendations
- Learning gradients via an early stopping gradient descent method
- Learning gradients by a gradient descent algorithm
- Early stopping and non-parametric regression: an optimal data-dependent stopping rule
- Online gradient descent learning algorithms
- Fast learning rates for regularized regression algorithms
Cited in
(only showing first 100 items - show all)- Bi-cross-validation for factor analysis
- Early stopping for statistical inverse problems via truncated SVD estimation
- Distributed regression learning with coefficient regularization
- Optimal learning rates for kernel partial least squares
- Distributed kernel-based gradient descent algorithms
- Regularization learning, early stopping and biased estimator
- The regularized least squares algorithm and the problem of learning halfspaces
- Adaptive kernel methods using the balancing principle
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- Distributed linear regression by averaging
- High-dimensional dynamics of generalization error in neural networks
- An elementary analysis of ridge regression with random design
- From inexact optimization to learning via gradient concentration
- Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
- A robust framework for identification of PDEs from noisy data
- Multidimensional item response theory in the style of collaborative filtering
- Distributed kernel gradient descent algorithm for minimum error entropy principle
- Data science applications to string theory
- Just interpolate: kernel ``ridgeless regression can generalize
- Smoothed residual stopping for statistical inverse problems via truncated SVD estimation
- Kernel gradient descent algorithm for information theoretic learning
- Theoretical investigation of generalization bounds for adversarial learning of deep neural networks
- Boosting with structural sparsity: a differential inclusion approach
- Balancing principle in supervised learning for a general regularization scheme
- Estimation of local degree distributions via local weighted averaging and Monte Carlo cross-validation
- Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
- Fast and strong convergence of online learning algorithms
- Learning gradients by a gradient descent algorithm
- Learning rates of gradient descent algorithm for classification
- Learning the mapping \(\mathbf{x}\mapsto \sum\limits_{i=1}^d x_i^2\): the cost of finding the needle in a haystack
- Kernel-based online gradient descent using distributed approach
- Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
- Side effects of learning from low-dimensional data embedded in a Euclidean space
- Synchronization and redundancy: implications for robustness of neural learning and decision making
- Least square regression with coefficient regularization by gradient descent
- Early stopping and non-parametric regression: an optimal data-dependent stopping rule
- Nonparametric stochastic approximation with large step-sizes
- Convergence Rates of Spectral Regularization Methods: A Comparison between Ill-Posed Inverse Problems and Statistical Kernel Learning
- Gradient-based Regularization Parameter Selection for Problems With Nonsmooth Penalty Functions
- Spectral Algorithms for Supervised Learning
- Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
- Consistency analysis of spectral regularization algorithms
- Boosting algorithms: regularization, prediction and model fitting
- Online learning for quantile regression and support vector regression
- Gradient descent for robust kernel-based regression
- Kernel methods in system identification, machine learning and function estimation: a survey
- Boosted kernel ridge regression: optimal learning rates and early stopping
- Distributed learning with regularized least squares
- Optimal rates for multi-pass stochastic gradient methods
- Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
- scientific article; zbMATH DE number 6860845 (Why is no real title available?)
- Generalization performance of multi-pass stochastic gradient descent with convex loss functions
- Analyzing the discrepancy principle for kernelized spectral filter learning algorithms
- scientific article; zbMATH DE number 7387623 (Why is no real title available?)
- Toward Efficient Ensemble Learning with Structure Constraints: Convergent Algorithms and Applications
- scientific article; zbMATH DE number 7306853 (Why is no real title available?)
- An algorithmic view of _2 regularization and some path-following algorithms
- Deep unfolding of a proximal interior point method for image restoration
- Semi-supervised learning with summary statistics
- Distributed learning with indefinite kernels
- Thresholded spectral algorithms for sparse approximations
- Learning theory of distributed spectral algorithms
- Online Pairwise Learning Algorithms
- Learning from non-identical sampling for classification
- A boosting inspired personalized threshold method for sepsis screening
- Implicit regularization with strongly convex bias: Stability and acceleration
- Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation
- Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
- Gradient estimation for smooth stopping criteria
- Capacity dependent analysis for functional online learning algorithms
- Large-dimensional random matrix theory and its applications in deep learning and wireless communications
- Nonparametric Functional Graphical Modeling Through Functional Additive Regression Operator
- Convergence rates of gradient methods for convex optimization in the space of measures
- Convex regularization in statistical inverse learning problems
- Effective stabilized self-training on few-labeled graph data
- Deep learning for natural language processing: a survey
- Gradient descent for deep matrix factorization: dynamics and implicit bias towards low rank
- Learning gradients via an early stopping gradient descent method
- On a nonlocal integral operator commuting with the Laplacian and the Sturm-Liouville problem: low rank perturbations of the operator
- A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems
- On the convergence of gradient descent for robust functional linear regression
- Fast iterative regularization by reusing data
- Iterative kernel regression with preconditioning
- Least squares approximations in linear statistical inverse learning problems
- Optimal rates for regularization of statistical inverse learning problems
- Convergence analysis of fractional Tikhonov scheme in learning theory
- Online learning algorithms tackling covariate shift
- Improved convergence rate of nested simulation with LSE on sieve
- SID-NET: machine learning based system identification framework for rigid and flexible multibody dynamics
- Minibatch and local SGD: algorithmic stability and linear speedup in generalization
- AP-MIONet: asymptotic-preserving multiple-input neural operators for capturing the high-field limits of collisional kinetic equations
- Minimum discrepancy principle strategy for choosing k in k-NN regression
- Limited memory bundle DC algorithm for sparse pairwise kernel learning
- Distributed learning with discretely observed functional data
- Adversarial contextual bandits go kernelized
- Iterative regularization in classification via hinge loss diagonal descent
- On the connections among three transfer learning paradigms
- Predicting pairwise interaction affinities with ℓ 0 -penalized least squares–a nonsmooth bi-objective optimization based approach*
- Synchronizing pretrained kernel regressors with applications to American option pricing
- Truncated kernel stochastic gradient descent on spheres
This page was built for publication: On early stopping in gradient descent learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2642922)
