Deep neural networks can interpolate any dataset in the overparametrized regime.
problem Interpolating any dataset with deep neural networks in the overparametrized regime.
method Proving universal approximations and interpolating any dataset with deep neural networks, considering specific conditions on activation functions.
result Interpolation of any dataset is possible in the overparametrized regime with deep neural networks.
Paper analyzes Gibbs and Langevin Monte Carlo for interpolation regime, showing generalization from low errors.
problem Analyzing Gibbs and Langevin Monte Carlo in overparameterized interpolation regime.
method Data-dependent bounds and stability under approximation with Langevin Monte Carlo.
result Generalization is signaled by small training errors in noisy regime, with bounds stable under approximation.
Algorithm solves American options with regime-switching using multigrid and compact finite difference.
problem Pricing American put options with regime-switching.
method Multigrid iterative algorithm based on compact finite difference schemes and Hermite interpolation.
result The algorithm provides a fast and efficient tool for pricing American put options with regime-switching.
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 shows overparameterization helps in generalizing from smooth interpolants.
problem Understanding generalization in overparameterized linear models.
method Analysis of random Fourier series model with weighted trigonometric interpolation.
result Weighted trigonometric interpolation leads to lower generalization error in overparameterized scenarios.
Interpolated-MLPs control inductive bias for better performance in low-compute tasks.
problem Low-compute performance gap between MLPs and CNNs.
method Introduced Interpolated MLP (I-MLP) approach to control inductive bias incrementally.
result Continuous logarithmic relationship between inductive bias and performance in low-compute tasks.
The study identifies conditions under which algorithmic stability explains generalization in interpolating learning systems.
problem Understanding when algorithmic stability explains generalization in interpolating learning systems.
method Modeling training as a function-space trajectory and measuring sensitivity to single-sample perturbations.
result There exist interpolating regimes with small risk where contractive sensitivity cannot hold, showing that stability is not a universal explanation.
New optimization method helps models generalize better after achieving near-perfect training performance.
problem Models can achieve near-perfect training performance but fail to generalize well to unseen examples.
method GROKtimizer combines rapid convergence to interpolation with post-interpolation norm minimization using Critically Damped Momentum.
result GROKtimizer provides a quadratic speedup over classical gradient descent, offering a natural solution for selecting low-norm interpolating solutions.
Deep ReLU networks need Ω(N) parameters to interpolate at irregularly spaced points.
problem Interpolating at irregularly spaced data points with deep ReLU networks.
method Analyzing the number of parameters required for interpolation.
result Ω(N) parameters are necessary for interpolation when δ is exponentially small in N.
Study finds exact limits for sparse regression with fewer observations than usual.
problem Understanding sparse linear regression with sublinear sparsity.
method Adaptive interpolation method and modified AMP algorithm.
result Exact asymptotic expressions for mutual information and MMSE in sublinear sparsity.
We consider a system of coupled free boundary problems for pricing American put options with regime-switching. To solve this system, we first employ the logarithmic transformation to map the free boundary for each regime to multi-fixed intervals and then eliminate the first-order derivative in the transformed model by …
SGD achieves near optimal convergence rate in smooth interpolation regime.
problem Optimization of smooth convex objectives with zero noise at optimum.
method Stochastic Gradient Descent (SGD) with large stepsize analysis.
result Last iterate of SGD achieves expected excess risk of O(1/T + σ* / √T) with optimal stepsize.
Traditionally in regression one minimizes the number of fitting parameters or uses smoothing/regularization to trade training (TE) and generalization error (GE). Driving TE to zero by increasing fitting degrees of freedom (dof) is expected to increase GE. However modern big-data approaches, including deep nets, seem to…
Bagging stabilizes linear interpolators, improving their generalization performance.
problem Unstable linear interpolators fail on noisy data.
method Introduced multiplier-bootstrap-based bagged least square estimator.
result Bagging effectively mitigates variance, leading to bounded prediction risk.
We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterization of the network fun…
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.
Study reveals learning curves and benign overfitting in spectral algorithms for large dimensions.
problem Understanding learning curves and benign overfitting in spectral algorithms for large-dimensional data.
method Analysis of learning curves and benign overfitting in spectral algorithms for inner-product kernels on the sphere and general domains.
result Characterization of three distinct regimes: over-regularized, under-regularized, and interpolation regimes, revealing benign overfitting across both under-regularized and interpolation regimes.
Near-interpolating models grow norms quickly, affecting generalization.
problem Understanding the trade-off between interpolation and generalization in near-interpolating models.
method Random matrix theory and eigendecay analysis of data covariance matrix.
result Near-interpolating models exhibit rapid norm growth and worse generalization trade-offs.
Interpolation can prevent classifiers from having desired invariance properties.
problem Invariance properties in over-parameterized models are often ineffective.
method Theoretical analysis and algorithm design for non-interpolating classifiers.
result Interpolating classifiers cannot satisfy desired invariance properties.
Interpolating estimators in nonparametric regression become suboptimal under adversarial attacks.
problem Adversarial robustness of interpolating estimators in nonparametric regression.
method Investigation of adversarial robustness of interpolating estimators in a nonparametric regression framework.
result Interpolating estimators must be suboptimal even under a subtle future X-attack. A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We investigate this overparameterized regime in linear regression, where all solut…
This paper analyzes multi-pass SGD for least squares, improving generalization bounds.
problem Improving generalization bounds for multi-pass SGD in the least squares problem.
method Develops an instance-dependent excess risk bound for least squares in the interpolation regime.
result SGD performs worse than GD instance-wise but saves computational time.
Lower bounds show OLS outperforms basis pursuit in overparameterized linear regression.
problem Excess risk of sparse interpolating procedures in overparameterized linear regression.
method Proved lower bounds on excess risk for OLS and basis pursuit.
result Excess risk of basis pursuit can converge at an exponentially slower rate than OLS.
Loose bounds found for least-norm interpolant in over-parameterized settings.
problem Failures of model-dependent generalization bounds for least-norm interpolation.
method Analysis of generalization performance of least-norm linear regressor in over-parameterized regime.
result Generalization bounds for least-norm interpolant can be very loose, even when true excess risk goes to zero.
Private optimization faster on interpolation problems with quadratic growth.
problem Private optimization in interpolation problems.
method Adaptive algorithm with improved sample complexity.
result Exponential improvement in private sample complexity for quadratic growth.
New method efficiently interpolates nonparametric density estimators.
problem Efficient evaluation of nonparametric density estimators.
method Piecewise multivariate polynomial interpolation scheme.
result New estimator with low space requirements and efficient querying.
Local Gradient Descent with local steps converges to the centralized model in the interpolation regime.
problem Understanding the implicit bias of Local Gradient Descent in the interpolation regime.
method Analyzing the implicit bias of Local Gradient Descent for classification tasks with linearly separable data.
result The aggregated global model from Local-GD converges exactly to the centralized model in the interpolation regime.
In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained to interpolate the data by driving the empirical loss (classification and regression) close to zero…
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.
Piecewise polynomial interpolation-based gradient descent reduces oracle complexity for smooth loss functions.
problem Optimizing empirical risk minimization loss functions
method Piecewise polynomial interpolation-based gradient descent
result Oracle complexity is reduced for smooth loss functions
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.
Many modern machine learning models are trained to achieve zero or near-zero training error in order to obtain near-optimal (but non-zero) test error. This phenomenon of strong generalization performance for "overfitted" / interpolated classifiers appears to be ubiquitous in high-dimensional data, having been observed …
This paper introduces a new bound to explain generalization in over-parameterized models.
problem Understanding why some over-parameterized models generalize well while others do not.
method PAC-Chernoff bounds and smoothness measures based on large deviation theory.
result Interpolators with smoother structures generalize better, according to the new theoretical framework.
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 resolves conjecture on overparameterized linear models' generalization.
problem Asymptotic generalization of multiclass classification with overparameterized models.
method Gaussian covariates bi-level model, Hanson-Wright inequality variant.
result Min-norm interpolating classifier can be suboptimal compared to noninterpolating classifiers.
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.
Stochastic gradient method converges as fast as deterministic for overparametrized models.
problem Convergence rate of stochastic gradient methods in overparametrized models.
method Proposes a regularity condition enabling fast convergence of SGD.
result Stochastic gradient method achieves the same convergence rate as deterministic gradient method.
New method interpolates training data and is consistent for various data distributions.
problem Establishing generalization guarantees for ensemble methods in the interpolating regime.
method Developed manifold-Hilbert kernel for Riemannian manifolds and used it in ensemble classification.
result Consistent ensemble classification method for broad data distributions.
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.
Study on clustering in high dimensions with anisotropic Gaussian mixtures, showing interpolation can be optimal and robust.
problem Clustering in high-dimensional anisotropic Gaussian mixtures.
method Derive minimax bounds, analyze ℓ2-regularized classifiers, and investigate interpolation's robustness. result Interpolating solutions can be optimal and robust under certain conditions.
Unified framework explains why overfitting is benign in interpolating learning.
problem Understanding why overfitting is benign in highly overparameterized models.
method Spectral-transport stability framework.
result Sharp benign-overfitting criterion and explicit phase-transition rates.
Deep neural networks can achieve remarkable generalization performances while interpolating the training data perfectly. Rather than the U-curve emblematic of the bias-variance trade-off, their test error often follows a "double descent" - a mark of the beneficial role of overparametrization. In this work, we develop a…
IIC provides a PAC-Bayes bound for interpolating models, revealing factors affecting generalization.
problem Theoretical challenges in understanding overparameterized models and their performance.
method PAC-Bayesian perspective applied to the Interpolating Information Criterion (IIC).
result Test error for overparameterized models achieving zero training error depends on various factors.
A new criterion selects models in overparameterized settings.
problem Model selection for overparameterized models with more parameters than data.
method Establishes Bayesian duality and introduces the Interpolating Information Criterion.
result The Interpolating Information Criterion selects models in overparameterized settings.
Study how generalization scales with model size and data in quadratic neural networks.
problem Understanding how generalization scales with model size and data in quadratic neural networks.
method Analyzed ℓ2-regularized empirical test error minimization in a quadratic two-layer network with finite-sample setting and structured data. result Revealed a phase diagram with distinct scaling regimes as the number of parameters varies, showing data-dependent power laws controlled by spectral structure of the target.
This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.
problem Understanding the interpolation error of nonlinear Attention in high-dimensional settings.
method Derives explicit expressions for mean-squared interpolation error using signal-plus-noise model and random matrix theory.
result Nonlinear Attention generally incurs a larger interpolation error than linear regression, but this gap can be reversed with structured signals.
Classification and regression tasks in overparameterized models show different generalization properties.
problem Comparing classification and regression in overparameterized models.
method Comparison of least-squares minimum-norm interpolation and hard-margin SVM using different loss functions.
result Interpolating solutions generalize well with 0-1 loss but not with square loss.
Matrix SMD converges to unique solution minimizing Bregman divergence.
problem High-dimensional multi-output classification and matrix completion problems.
method Stochastic Mirror Descent with matrix parameters and matrix mirror functions.
result Matrix SMD converges exponentially to the unique solution minimizing Bregman divergence.