This paper explores adaptive methods in over-parameterized linear regression.
problem Understanding why neural networks generalize well in over-parameterized settings.
method Characterizes two sub-classes of adaptive methods and their generalization performance.
result Adaptive methods in over-parameterized linear regression converge to the minimum norm solution.
New methods solve tensor-on-tensor regression with unknown rank, revealing benefits of over-parameterization.
problem Connecting tensor responses to tensor covariates with unknown intrinsic rank.
method Riemannian gradient descent and Riemannian Gauss-Newton methods for tensor-on-tensor regression.
result Riemannian optimization methods converge linearly and quadratically to a statistically optimal estimate in rank over-parameterized settings.
Paper explores how design matrix patterns affect regression performance in over-parameterized models.
problem The impact of covariance matrix degeneracy and covariate dependence on regression performance in over-parameterized models.
method Derives deterministic equivalents for prediction risk in a vanishing-ridge regime, using graph theory to identify singular configurations.
result Degeneracy of covariance matrices and dependence can lead to multiple descent in regression performance.
New geometric interpretation explains over-parameterized models and adversarial perturbations.
problem Geometric understanding of over-parameterized regression and adversarial perturbations.
method Alternative geometric interpretation of regression in feature space.
result Adversarial perturbations are a natural feature of biased models due to underlying geometry.
The paper explores how over-parameterized linear regression models generalize without violating learning theory principles.
problem Understanding how over-parameterized linear regression models generalize without violating learning theory principles.
method The paper uses the predictive normalized maximum likelihood (pNML) learner to investigate the minimum norm solution of over-parameterized linear regression models.
result The model generalizes well when the test sample lies in a subspace spanned by eigenvectors associated with large eigenvalues of the training data.
Improves adaptivity in sequence models by over-parameterizing.
problem Adaptivity and generalization in sequence models.
method Over-parameterized gradient descent using eigenfunctions.
result Over-parameterization enhances model adaptivity and generalization.
The paper analyzes optimal implicit bias in linear regression for over-parameterized models.
problem Finding the best generalization performance in over-parameterized linear regression.
method Asymptotic analysis of generalization performance for convex functions/potentials.
result Optimal implicit bias that achieves the best generalization error under certain conditions.
Knoop enhances variable selection with over-parameterization and knockoffs.
problem Challenges of variable selection in high-dimensional datasets.
method Generates knockoff variables, integrates them into an over-parameterized model, and uses anomaly-based significance tests.
result Superior performance in variable selection compared to existing methods.
Over-parameterized CNNs show U-shaped test risk with depth increase.
problem Understanding the impact of depth on test risk in over-parameterized CNNs.
method Empirical image classification experiments and linear regression framework.
result Test risk is U-shaped with increasing depth in over-parameterized CNNs.
Study shows how over-parameterized classifiers can still perform well on noisy data.
problem Understanding how maximum margin classifiers perform in over-parameterized settings with noisy data.
method Analyzes maximum margin classifiers on sub-Gaussian mixtures, providing risk bounds.
result Characterizes conditions for 'benign overfitting' in linear classification problems.
Gradient descent trains neural networks to match kernel regression's sharp generalization rate.
problem Training over-parameterized neural networks for nonparametric regression.
method Gradient descent with early stopping on over-parameterized two-layer neural networks.
result Trained neural networks achieve sharp generalization rate of O(εn2). The study identifies spurious correlations in high-dimensional regression and quantifies their impact.
problem Spurious correlations in high-dimensional regression models.
method Statistical characterization of spurious correlations, quantifying their amount via ridge regularization.
result The value of regularization strength that minimizes test loss is in an interval where spurious correlations increase.
Gradient Descent with Projection learns low-degree polynomials efficiently.
problem Learning low-degree spherical polynomials with neural networks.
method Over-parameterized two-layer neural network with Gradient Descent with Projection.
result Achieves nearly minimax optimal sample complexity and risk bound.
Analyzes generalization error in generalized linear models, explaining double descent phenomenon.
problem Understanding generalization of machine learning models in high dimensions.
method Develops a framework to characterize asymptotic generalization error for generalized linear models.
result Rigorously explains the double descent phenomenon in generalized linear models.
Proposes a continuous, differentiable model from local adaptive models.
problem Inadequate continuity and differentiability in over-parameterized models.
method A global continuous and differentiable model constructed from weighted averages of locally learned models.
result Achieves faster statistical convergence and improved performance in various settings.
Bayesian interpretation explains double descent in deep learning models.
problem Understanding the risk function behavior of over-parameterized models.
method Bayesian model selection, Dickey-Savage ratio, ridge regression, global-local shrinkage.
result Double descent phenomenon explained through Bayesian interpretation.
Study reveals benign overfitting in time series models with over-parameterization.
problem Analyzing over-parameterized linear models with dependent time-series data.
method Developed an estimator using interpolation and derived non-asymptotic risk bounds.
result Risk bound is influenced by the coherence of temporal covariance matrices at different time steps.
Deep neural networks can learn smooth functions without parameters.
problem Learning smooth functions from shallow ReLU neural networks.
method Using over-parameterized shallow ReLU neural networks with norm constraints.
result Least squares estimators based on shallow neural networks are minimax optimal.
The paper studies the minimum ℓ₁-norm interpolator's risk behavior in over-parameterized settings.
problem Understanding the risk behavior of minimum ℓ₁-norm interpolators in high-dimensional settings.
method Exact characterization of the risk behavior through a system of two non-linear equations.
result Observation of a multi-descent phenomenon in the generalization risk of the minimum ℓ₁-norm interpolator.
Improved autoencoders show joint training benefits over weak training.
problem Improving unsupervised learning performance with over-parameterized networks.
method Analyzing gradient dynamics of two-layer autoencoders with ReLU activation, proving linear convergence in weakly-trained and jointly-trained regimes.
result Joint training leads to better global optima and requires less over-parameterization.
New insights into bias and variance in over-parameterized models.
problem Understanding bias and variance in over-parameterized models.
method Analytic expressions derived from statistical physics for two minimal models.
result Over-parameterized models can overfit even in noiseless conditions.
Optimal rates for shallow ReLU networks in nonparametric regression.
problem Approximating smooth and non-smooth functions with shallow ReLU networks.
method Analysis of shallow ReLUk neural networks, using variation norms and deep learning theory. result Optimal approximation rates for shallow ReLU networks in nonparametric regression.
Enhances data augmentation for regression tasks.
problem Limited effectiveness of data augmentation in regression.
method Curvature-Enhanced Manifold Sampling (CEMS).
result CEMS improves performance in regression tasks.
Neural networks trained with PGD achieve sharp regression rates in interpolation spaces.
problem Nonparametric regression using over-parameterized neural networks in interpolation spaces.
method Over-parameterized two-layer neural networks trained with Preconditioned Gradient Descent (PGD) and early stopping.
result Achieves a sharp regression rate of \(\cO(n^{-\frac{2αs'}{2αs'+1}})\) in interpolation spaces \(\bth{\cH_K}^{s'}\).
Exact expressions for double descent and implicit regularization in over-parameterized models.
problem Understanding the generalization error of over-parameterized models like deep neural networks.
method Surrogate random design to replace standard i.i.d. design, leading to exact expressions for mean squared error and implicit regularization.
result Exact non-asymptotic expressions for double descent and implicit regularization in over-parameterized models.
The paper proposes a gradient-based method for multi-penalty Ridge regression.
problem Optimizing multiple regularization hyperparameters for linear regression.
method Gradient-based optimization through matrix differential calculus.
result The method outperforms traditional regularization techniques like LASSO and Ridge.
MAML with over-parameterized DNNs converges globally at a linear rate.
problem Few-shot learning with limited data.
method Model-agnostic meta-learning (MAML) with over-parameterized deep neural networks (DNNs).
result MAML with over-parameterized DNNs converges globally at a linear rate.
Geometric Occam's Razor shapes deep learning solutions.
problem Understanding the regularization in over-parameterized neural networks.
method Analyzing the geometric model complexity and Dirichlet energy in neural networks.
result Over-parameterized neural networks are implicitly regularized by geometric model complexity.
Recently, several studies have proven the global convergence and generalization abilities of the gradient descent method for two-layer ReLU networks. Most studies especially focused on the regression problems with the squared loss function, except for a few, and the importance of the positivity of the neural tangent ke…
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature. To address this issue, several highly flexible and scalable variational inference procedures based on the idea of particle optimization have be…
New approach to bilevel optimization for machine learning using functional methods.
problem Solving bilevel optimization problems in machine learning, especially with over-parameterized neural networks.
method Functional point of view, scalable and efficient algorithms for functional bilevel optimization.
result Demonstrates benefits of functional approach on instrumental regression and reinforcement learning tasks.
Study on ridge regression in convolutional models shows double descent error behavior.
problem Understanding generalization and estimation error in over-parameterized convolutional models.
method Analysis of ridge estimators for convolutional linear models, derivation of exact error formulae.
result Ridge estimators exhibit double descent error behavior in high-dimensional convolutional models.
Unified scheme combining softmax and ResNet for deep learning.
problem Combining softmax and ResNet for deep learning.
method Theoretical analysis of a unified scheme combining softmax regression and ResNet.
result Unified scheme connects previously unrelated fields and provides insights into loss landscape and optimization.
Paper explores why overfitted DNNs in adversarial training can generalize.
problem Understanding why overfitted DNNs in adversarial training can generalize despite poor robust generalization.
method An approximation viewpoint to analyze the robust overfitting of over-parameterized DNNs.
result Existence of infinitely many overfitted DNNs that achieve good robust generalization under certain conditions.
Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.
problem Robust recovery of low-rank matrices from grossly corrupted measurements.
method Gradient descent with discrepant learning rates for double over-parameterized models.
result Gradient descent with discrepant learning rates provably recovers the underlying matrix without prior knowledge on rank or sparsity.
New method improves deep learning models robustness to label noise.
problem Improving deep learning models' robustness to corrupted labels.
method Sparse over-parameterization and implicit regularization.
result State-of-the-art test accuracy against label noise on various datasets.
The paper bounds neural networks' approximation error and applies it to regression and GANs.
problem Bounding the approximation error of norm-constrained neural networks.
method Proved upper and lower bounds on approximation error using Rademacher complexity.
result Obtained convergence rates for over-parameterized neural networks and optimal GAN learning rates.
The paper studies multiple descent in multi-component prediction models.
problem Understanding the risk curves in multi-component prediction models.
method Investigates a 'double random feature model' and 'multiple random feature model' in ridge regression.
result Risk curves of multi-component prediction models can exhibit multiple descents.
New framework explains why over-parameterized neural networks work well.
problem Why over-parameterized neural networks perform well in practice.
method Neural feature repopulation framework using gradient descent.
result Over-parameterized two-level neural networks learn near optimal feature distributions.
Local convergence theory for mildly over-parameterized neural nets.
problem Understanding why over-parameterization works in neural networks.
method Developed a local convergence theory for two-layer neural nets, showing neuron convergence under certain conditions.
result All student neurons converge to one of teacher neurons when the loss is below a threshold.
New insights into optimization and generalization for linear models.
problem Understanding the implicit regularization of optimization methods for linear models.
method Investigating the norms minimized by interpolating solutions and using projections to move between solutions.
result Proving that for over-parameterized linear classification, projections onto the data-span enable the use of under-parameterized techniques.
Study optimizes linear regression analysis for high-dimensional settings.
problem Understanding high-dimensional linear regression with interpolation and regularization.
method Localized uniform convergence analysis of optimistic rates for linear regression.
result Recover guarantees for ridge and LASSO regression under random designs.
Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very recently, a line of work explains in theory that with over-parameterization and p…
Deeper models have a more favorable optimization landscape, making them more robust to noise.
problem Characterizing the effect of depth on the optimization landscape of linear regression models.
method Robust and over-parameterized setting, simple sub-gradient method.
result A simple sub-gradient method converges to a balanced solution that is close to the ground truth and enjoys a flat local landscape.
Supporting evidence for adaptive feature program across diverse models.
problem Analyzing feature learning in neural networks.
method Over-parameterized sequence models and feature error measure (FEM).
result FEM is decreasing during training of adaptive feature models.
This work improves the lottery ticket hypothesis by reducing over-parameterization requirement.
problem Approximating a neural network by pruning a randomly over-parameterized network.
method Connecting pruning ReLU networks to extsc{SubsetSum} problem, showing logarithmic over-parameterization sufficiency.
result Logarithmic over-parameterization is sufficient for approximating any target neural network.
Linear models can overfit without harming OOD generalization under certain conditions.
problem Understanding how overparameterized linear models generalize to out-of-distribution data.
method Analyzing overparameterized linear models under covariate shift, providing guarantees for OOD generalization.
result Benign overfitting occurs in standard ridge regression under OOD conditions, with specific structural conditions on target covariance.
Least squares regression shows unexpected double descent in under-parameterized models.
problem Understanding the generalization of under-parameterized models in regression.
method Analyzing the spectrum and eigenvectors of the sample covariance matrix.
result Least squares regression can exhibit a peak in generalization in the under-parameterized regime, contrary to previous explanations.