Interpolation hurts robust generalization even without noise.
problem The challenge of robust generalization in the absence of noise.
method Avoiding interpolation through ridge regularization.
result Ridge regularization improves robust generalization.
We analyze ridge interpolators in correlated factor regression models using RDT.
problem Performance analysis of ridge interpolators in correlated factor regression models.
method Utilizing Random Duality Theory (RDT), we obtain precise closed form characterizations of optimization problems.
result Ridge interpolators can smooth out the excess prediction risk and exhibit double-descent behavior.
Interpolating models can have heavy-tailed risk, leading to rare but severe errors.
problem Interpolating models' tail risk is poorly understood, affecting rare but impactful errors.
method Large-deviation methods to study the fragility of high-dimensional linear interpolators.
result Ridgeless regression exhibits heavy-tailed risk, while ridge-regularized estimators have better tail behavior.
Study shows minimizing the norm of the ERM solution stabilizes kernel ridge-less regression.
problem Stability of kernel ridge-less regression.
method Minimizing the norm of the ERM solution to minimize CV stability.
result Interpolating solution with minimum norm minimizes CV stability.
Neural networks can interpolate random data but still generalize well, studied in the NT regime.
problem Understanding how neural networks interpolate random labels and generalize well in the overparametrized regime.
method Characterization of the eigenstructure of the empirical NT kernel and generalization error of NT ridge regression.
result The generalization error is well approximated by polynomial ridge regression with an increased regularization parameter.
Study on learning properties of scale-dependent kernels controlling stability and error.
problem Understanding the learning properties of scale-dependent kernels in nonparametric ridge-less least squares.
method Combines probabilistic results with interpolation theory to analyze stability and error.
result Different regimes of learning error depending on sample size and data dimension.
New study finds many neural networks are not benignly overfitting.
problem Understanding the behavior of overfitting in neural networks.
method Exploring kernel ridge regression and deep neural networks to identify overfitting behaviors.
result Many interpolating methods, including neural networks, exhibit tempered overfitting rather than benign or catastrophic.
Study precise estimators for correlated data using RDT.
problem Analyzing estimators in correlated linear regression models.
method Utilized Random Duality Theory to characterize prediction risk.
result Precise closed form characterizations of estimators' risk.
Ridge regression analysis under varying sample size and dimensionality.
problem Prediction error analysis in asymptotic ridge regression.
method Characterization of prediction error based on covariance and parameter structure.
result Interpolation can be optimal even with bounded SNR if true parameter coefficients are larger on high-variance directions.
Inflating the minimum norm interpolator improves linear regression generalization error.
problem Highly anisotropic covariances and diverging d/n in linear regression. method Inflating the minimum ℓ2 norm interpolator by a constant greater than one. result Inflating the minimum norm interpolator improves generalization error.
Optimal rates for vector-valued regression on various norms.
problem Optimal rates for vector-valued ridge regression on continuous norms.
method Combining standard capacity assumptions with tensor product constructions of vector-valued interpolation spaces.
result Optimal rates for vector-valued ridge regression, independent of output space dimension.
Kernel balancing weights are generalized as KRRR, providing better confidence intervals for treatment effects.
problem Lack of generalization error, correct feature specification, and limited to average effects.
method Interpreting kernel balancing weights as KRRR, relaxing feature specification, and extending Gaussian approximation.
result KRRR provides strong generalization properties and justifies confidence sets for causal functions.
The study prevents model collapse in overparameterized linear regression by mixing real and synthetic labels.
problem Preventing model collapse in overparameterized linear regression.
method Iterative mixing of real and synthetic labels, deriving generalization error formulae.
result Optimal mixing ratio converges to the reciprocal of the golden ratio for isotropic features.
Manifold learning has been successfully applied to a variety of medical imaging problems. Its use in real-time applications requires fast projection onto the low-dimensional space. To this end, out-of-sample extensions are applied by constructing an interpolation function that maps from the input space to the low-dimen…
This paper introduces an interpolation-based method, called the reconstruction approach, for nonparametric regression. Based on the fact that interpolation usually has negligible errors compared to statistical estimation, the reconstruction approach uses an interpolator to parameterize the regression function with its …
New findings on how overfitting can be beneficial in ridge regression.
problem Understanding overfitting in overparameterized models.
method Extending previous results on linear regression to ridge regression, eliminating independence assumptions.
result Sharp bounds on the variance and bias terms, explaining optimal regularization in ridge regression.
Develops interpolation methods for matrix functions in statistics and machine learning.
problem Estimating matrix functions in statistics and machine learning.
method Interpolates log-determinant and trace of matrix powers using modified sharp bounds.
result Accuracy and performance demonstrated in numerical examples.
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.
Study the cost of overfitting in noisy KRR models.
problem Cost of overfitting in noisy kernel ridge regression.
method An agnostic view of overfitting cost as a function of sample size for any target function, using Gaussian universality ansatz and task eigenstructure.
result Characterization of benign, tempered, and catastrophic overfitting.
Ridge regression shows different behaviors in binary classification with noisy labels.
problem Binary classification with noisy labels and anisotropic cluster distributions.
method Investigation of ridge regression behavior in overparameterized settings with label noise.
result Ridge regression exhibits qualitatively different behavior based on the scale of cluster mean vectors and covariance matrices.
A new tradeoff between regularization and sharpness improves model performance in overparameterized settings.
problem Improving model performance in overparameterized settings with minimum-norm interpolators.
method Proposes a regularization-sharpness tradeoff for overparameterized linear regression with an ℓ^p penalty.
result Empirical validation shows the tradeoff terms can distinguish performant linear interpolators.
Regression models can interpolate noisy data and still perform well, contrary to the bias-variance tradeoff.
problem Understanding why overparametrized models can generalize well despite the bias-variance tradeoff.
method Analysis of minimum norm solutions and ridge regression, focusing on the smallest singular value of the regression matrix.
result Testing error exhibits double descent behavior as model order increases, contrary to the classical bias-variance tradeoff.
Study shows neural collapse is invariant to class imbalances under certain conditions.
problem Neural collapse properties are only valid for balanced data.
method Adopted UFM and introduced SELI for invariant characterization.
result Embeddings and classifiers always interpolate a simplex-encoded label matrix regardless of class imbalances.
Paper investigates optimal interpolation methods in linear regression.
problem Understanding when interpolating methods generalize well in linear regression.
method Investigates optimal response-linear interpolators using functions linear in the response variable.
result Provides a closed-form expression for the optimal interpolator and shows it can be derived as the limit of gradient descent.
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.
Study interpolating estimators for causal learning from observational data.
problem Learning causal models from observational data in complex model classes.
method Investigate min-norm interpolators and ridge-regularized regressors in a linearly confounded model.
result Interpolators cannot be optimal for causal learning under the principle of independent causal mechanisms, requiring stronger regularization.
Study optimizes learning rates for conditional mean embedding estimates.
problem Consistency of kernel ridge regression for conditional mean embedding.
method Adaptive statistical learning rate derived for misspecified setting.
result Upper bound matches optimal O(logn/n) rates without assuming finite dimensionality. Adversarial training improves linear regression solutions, revealing sparsity and abrupt interpolation.
problem Adversarial attacks on linear regression models.
method Formulated as a convex problem, adversarial training is used to find robust solutions that are sparse and interpolate data.
result Adversarial training with small disturbances gives the solution with the minimum-norm that interpolates the training data, revealing abrupt transition into interpolation.
This research uses DPPs to improve semi-parametric regression models.
problem Improving comprehensibility in semi-parametric regression models without sacrificing accuracy.
method Introduced a novel representation of finite DPPs and used it to derive a key identity illustrating implicit regularization.
result Demonstrated the implicit regularization effect of determinantal sampling for semi-parametric regression.
This work studies finite-sample properties of the risk of the minimum-norm interpolating predictor in high-dimensional regression models. If the effective rank of the covariance matrix Σ of the p regression features is much larger than the sample size n, we show that the min-norm interpolating predictor is not de…
New ridge regression bounds for high-dimensional data without proportional growth.
problem Moving beyond proportional asymptotics in high-dimensional statistics.
method Revisits ridge regression on i.i.d. data, allowing high-dimensional or infinite-dimensional feature vectors.
result Establishes non-asymptotic bounds approximating bias and variance of ridge regression.
STARK improves denoising of low-depth spatial transcriptomics images.
problem Denoising spatial transcriptomics images at ultra-low sequencing depths.
method Adaptive regularization with kernel ridge regression and graph Laplacian.
result STARK optimizes denoising performance over competing methods.
Regularized linear regression improves binary classification performance, especially with ridge and ℓ1 regularization.
problem Improving binary classification accuracy with noisy labels.
method Systematic study of regularization strengths on linear classifiers trained on noisy binary classification data.
result Ridge regression consistently improves classification error, while ℓ1 regularization can induce sparsity and ℓ∞ regularization can concentrate weights to two values. New method stabilizes machine learning for physics-informed inverse problems.
problem Reconstructing physical quantities from PDE-compliant measurements.
method Physics-informed learning with smooth inductive bias.
result PDE operators stabilize variance and prevent overfitting in fixed dimensions.
Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.
problem Understanding and quantifying data poisoning in linear models.
method Analysis of ridge least squares with an unpenalized intercept, using resolvent techniques and random matrix theory.
result Closed-form limits for the poisoned score, revealing scaling laws and weight alignment with the poisoning direction.
New insights into how large models can interpolate noisy data and still generalize well.
problem Understanding how large models can interpolate noisy data and still generalize well.
method Conceptual shift focusing on almost benign overfitting, analyzing sample size and model complexity.
result Large models can achieve both good training fit and Bayes-optimal generalization even in classical regimes.
Paper introduces a novel framework for supervised graph prediction using Optimal Transport.
problem Supervised labeled graph prediction.
method Fused Gromov-Wasserstein (FGW) loss and FGW barycenter with neural network weights and learned graphs.
result The method can interpolate in the labeled graph space and achieve good performance on difficult problems.
Noiseless KRR achieves optimal rates and exhibits saturation effects.
problem Understanding optimal rates and saturation phenomena in noiseless kernel ridge regression.
method Comprehensive study of noiseless KRR, establishing minimax optimal rates and uncovering phenomena of extra-smoothness and saturation.
result Noiseless KRR achieves minimax optimal rates and exhibits saturation effects.
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.
The paper proves a non-asymptotic test error approximation for KRR.
problem Understanding the test error of Kernel Ridge Regression.
method Established a non-asymptotic deterministic approximation for test error of KRR.
result The test error of KRR can be approximated by a closed-form estimate derived from the spectrum of the kernel operator.
Adversarial training improves linear regression solutions, offering robustness against small perturbations.
problem Vulnerability of linear models to adversarial perturbations.
method Formulated as a min-max problem, adversarial training minimizes the best solution under worst-case attacks.
result Adversarial training yields the minimum-norm interpolating solution in overparameterized models, equivalent to parameter shrinking methods in underparameterized models.
Two new algorithms recover ridge lines from point clouds with convergence guarantees.
problem Extracting filamentary structure from point clouds.
method Proposes two novel algorithms with convergence guarantees.
result The algorithms can asymptotically recover the full ridge set.
The original Broad Learning System (BLS) on new added nodes and its existing efficient implementation both assume the ridge parameter lambda -> 0 in the ridge inverse to approximate the generalized inverse, and compute the generalized inverse solution for the output weights. In this paper, we propose two ridge solution…
Optimal self-distillation improves generative models' velocity risk and mode recovery.
problem Improving generative models' velocity risk and mode recovery.
method Proved optimal self-distillation for rectified flow via linear probing, derived mixing coefficient, and provided validation tuning.
result Optimal self-distillation improves velocity risk and mode recovery.
Ridge regularization simplifies model complexity in data science.
problem Overfitting in statistical models.
method Adding a penalty on the magnitude of coefficients.
result Effective in reducing model complexity and improving generalization.
We study the problem of estimating the ridges of a density function. Ridge estimation is an extension of mode finding and is useful for understanding the structure of a density. It can also be used to find hidden structure in point cloud data. We show that, under mild regularity conditions, the ridges of the kernel den…
Improved ridge estimators avoid tuning parameters for high-dimensional data.
problem Difficulty in calibrating tuning parameters for ridge estimators.
method Developed modified ridge estimators that eliminate tuning parameters.
result Modified ridge estimators outperform standard methods in prediction accuracy.
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks. While it has been empirically observed that flatness measures consistently correlate strongly with generalization, it is still an open theoretical problem why and under whic…