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.
Advances smooth over-parameterization for solving non-smooth optimization problems.
problem Non-smooth optimization with structural constraints in imaging and machine learning.
method Smooth over-parameterization of non-smooth problems, using gradient descent and mirror descent.
result Gradient descent on the reformulated smooth problem converges efficiently without parameter tuning.
Adaptive gradient methods converge faster with over-parameterization and line-search.
problem Training over-parameterized models using adaptive gradient methods.
method Simplified setting of smooth, convex losses with over-parameterized models, proving convergence rates and demonstrating improvements with line-search techniques.
result Adaptive gradient methods, particularly AMSGrad, converge faster with line-search techniques.
Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee convergence to a stationary point. We propose an adaptive gradient method and show t…
Gradient descent slows significantly in over-parameterized single neuron learning.
problem Learning a single neuron with over-parameterization and square loss.
method Analysis of gradient descent dynamics, proving convergence rates and lower bounds.
result Over-parameterization can exponentially slow down the convergence rate of gradient descent.
Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural networks with one hidden layer. The theory of multi-layer networks remains largely …
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.
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.
State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain over-parameterized regime, the learning dynamics of gradient descent are governed …
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…
A boosting method improves nonparametric density estimation without smoothing assumptions.
problem Overfitting in nonparametric data fitting.
method Introduces a boosting algorithm for univariate nonparametric maximum likelihood estimation.
result Demonstrates the effectiveness of the boosting approach through simulations and real data experiments.
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.
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.
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.
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.
The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. Though techniq…
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.
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.
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…
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.
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.
Gradient EM converges globally for over-parameterized Gaussian mixtures.
problem Global convergence of gradient EM for Gaussian mixtures with more than 2 components.
method Likelihood-based convergence analysis framework.
result Gradient EM converges globally with a sublinear rate of O(1/√t).
Over-parameterization makes optimization easier for simple neural networks, even with minor extra neurons.
problem Understanding the impact of over-parameterization on optimization landscapes of shallow neural networks.
method Analyzing a simple ReLU neural network with Gaussian inputs, focusing on optimization properties and landscape changes.
result Over-parameterization makes the objective function one-point strongly convex in most directions, aiding optimization.
DEQs converge to optimal solutions with mild over-parameterization.
problem Training over-parameterized deep equilibrium models.
method Solves equilibrium point directly, uses gradient descent, and analyzes convergence via linear rate.
result Gradient descent converges to a globally optimal solution at a linear rate for quadratic loss.
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 bounds graph neural networks' over-parameterized error.
problem Understanding graph neural networks' performance in over-parameterized regimes.
method Developed mean-field regime bounds for graph convolutional and message passing neural networks.
result Established upper bounds with a convergence rate of O(1/n) for generalization error. 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.
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.
One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies this surprising phenomenon for two-layer fully connected ReLU activated neural n…
New method to recover over-parameterized models corrupted during estimation.
problem Recovering statistical models corrupted after initial estimation.
method Robust estimation using over-parameterized models and redundancy.
result Stochastic gradient descent is well-suited for model repair, but sparsity is generally not repairable.
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.
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.
This work proposes a mathematical framework for loss landscapes and optimization in deep neural networks.
problem The effectiveness of gradient-based optimization in over-parameterized neural networks.
method A modern view and mathematical framework of loss landscapes and efficient optimization in over-parameterized machine learning models.
result Wide neural networks satisfy the PL∗ condition, explaining (S)GD convergence to a global minimum. 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.
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.
Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we present a new theoretical framework for analyzing over-parameterized neural networks …
PrecGD restores linear convergence in over-parameterized nonconvex matrix factorization.
problem Slow convergence of local search algorithms in over-parameterized nonconvex matrix factorization.
method Preconditioned Gradient Descent (PrecGD) with an inexpensive ℓ2 regularization. result PrecGD restores linear convergence rate even in the over-parameterized case.
Expectation Maximization (EM) is among the most popular algorithms for maximum likelihood estimation, but it is generally only guaranteed to find its stationary points of the log-likelihood objective. The goal of this article is to present theoretical and empirical evidence that over-parameterization can help EM avoid …
Over-parameterized models can memorize noisy labels and still generalize well, revealing a hidden structure.
problem Understanding how over-parameterized models can simultaneously memorize noisy labels and generalize well.
method Investigated through modular arithmetic tasks with label noise using two-layer neural networks.
result Over-parameterized models can achieve near-perfect test accuracy with 80% label noise by extracting an internal generalization structure.
A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generalization capacity) in the regime where they are massively over-parameterized. Consequently, over the past year, the community has devoted growin…
Deep learning models can generalize well even when they fit training data perfectly.
problem Generalization in over-parameterized deep learning models.
method Combining empirical risk minimization with capacity control, exploring inductive biases and smooth empirical risk minimizers.
result Double descent phenomenon: test error can decrease after interpolation point.
In this paper, we analyze the effects of depth and width on the quality of local minima, without strong over-parameterization and simplification assumptions in the literature. Without any simplification assumption, for deep nonlinear neural networks with the squared loss, we theoretically show that the quality of local…
Sub-gradient method recovers low-rank matrices robustly from noisy measurements.
problem Recovering low-rank matrices from noisy measurements with unknown rank.
method Sub-gradient method with small initialization, robust to over-parameterization and noise.
result Sub-gradient method converges exponentially fast to the true solution under noisy and over-parameterized conditions.
The paper explains how ReLU nets converge globally in high dimensions without strict assumptions.
problem Understanding global convergence of ReLU nets in very high dimensions.
method Fine-grained analysis of random activation matrices and detailed gradient norm and curvature analysis.
result Empirical loss function has favorable geometrical properties in the overparameterized setting.
This paper optimizes learning from data with over-parameterization.
problem Learning an unknown function from data with various model assumptions.
method Solving a discrete over-parameterized optimization problem with a penalty term.
result Near optimal approximation of the function f can be found. This paper proves SGD converges to global minimum for over-parameterized ReLU networks.
problem Theoretical understanding of implicit neural networks is limited.
method Gradient flow analysis of ReLU activated implicit neural networks.
result Randomly initialized gradient descent converges to global minimum at a linear rate for square loss function in over-parameterized ReLU networks.
Over-parameterized models reduce Out-of-Distribution (OOD) generalization loss.
problem Understanding how over-parameterized models handle non-trivial distributional shifts.
method Investigating random feature models and examining non-trivial natural distributional shifts.
result Increasing model parameterization reduces OOD loss.