New approach shows why overparameterized neural nets generalize well.
problem Understanding why overparameterized neural nets generalize well in practice.
method An alternative notion of capacity for attention-based models based on the effective rank of attention matrices.
result Generalization bound matches empirical scaling laws observed in large language models.
This work finds a point with small test error in polynomial time for mildly overparameterized neural nets.
problem Achieving small test error in mildly overparameterized neural networks.
method The work shows that the landscape of loss functions with explicit regularization has a property that all local minima and certain stationary points achieve small test error. It also proves the existence of polynomial time algorithms for finding such points in convolutional and fully connected neural nets.
result Polynomial time algorithms exist for finding points with small test error in mildly overparameterized neural nets.
We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from Rn to R - in particular, nonconvex, with discrete global minima. In this paper, we prove that in at least one impo…
Improved TD learning with neural nets reduces sample complexity and overparameterization.
problem Temporal difference learning with neural networks in large state spaces.
method Projection-free and max-norm regularized Neural TD learning, with Lyapunov drift analysis.
result Max-norm regularization significantly improves TD learning's sample complexity and overparameterization.
Sobolev training helps neural nets fit function values and derivatives.
problem Training neural nets to match function values and derivatives accurately.
method Using Sobolev loss with gradient flow for overparameterized networks.
result Gradient flow from random initialization can fit any function and its derivatives.
New algorithm reduces neural net error in contextual bandits.
problem Neural contextual bandits with general activation functions.
method Proposed an efficient algorithm with sublinear regret bound.
result Demonstrated provably sublinear regret bound in finite regime.
Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the capacity to fit any set of labels including random noise. However, given the hi…
This study shows neural nets can approximate Turing machines with meaningful statistical properties.
problem Theoretical limitations in approximating Turing machines with neural networks.
method Formal definition of statistically meaningful approximation, analysis of boolean circuits and Turing machines using neural nets.
result Transformers can statistically meaningfully approximate Turing machines with polynomial sample complexity.
The paper explains how simple methods can converge to optimal solutions in complex neural games.
problem Finding optimal solutions in neural games with non-convex objectives.
method Theoretical framework using hidden convexity and overparameterization, with path-length bounds and PŁ conditions.
result Simple gradient methods can converge to Nash equilibria in non-convex min-max games under certain conditions.
GD with early stopping trains shallow neural nets for nonparametric regression robustly.
problem Learning Lipschitz regression functions with noisy labels.
method Overparameterized shallow neural networks trained by GD with early stopping.
result Optimal rates of convergence for nonparametric regression.
Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works: (i) Using a tighter char…
GD-trained shallow ReLU nets learn Lipschitz functions with noise.
problem Learning Lipschitz functions with additive noise in overparameterized neural networks.
method Gradient Descent (GD) with early stopping, focusing on the Neural Tangent Kernel (NTK).
result Early-stopped GD achieves minimax optimal rates for learning Lipschitz functions.
PSiLON Net uses L1 weight normalization and 1-path-norm regularization for efficient learning and sparsity.
problem Efficient learning and sparsity in neural networks with limited data.
method PSiLON Net employs L1 weight normalization and 1-path-norm regularization to simplify the 1-path-norm and achieve efficient learning and near-sparse parameters. result PSiLON Net achieves reliable optimization and strong performance in the small data regime.
This paper explains how overparameterization aids in meta-learning with few samples.
problem Building a generalizable model with few samples in meta-learning.
method Analyzes the optimal linear representation and sample complexity for meta-learning tasks.
result Overparameterization naturally answers fundamental meta-learning questions, reducing sample complexity.
Uniform bounds for neural networks' generalization error in overparameterized settings.
problem Generalization error in overparameterized neural networks.
method Neural Tangent kernel theory and Mercer decomposition of the NT kernel in spherical harmonics.
result Uniform generalization bounds for overparameterized neural networks in RKHS.
This work explains how large neural networks generalize well despite overparameterization.
problem Understanding the generalization behavior of large neural networks.
method Theoretical analysis of approximation and generalization errors in regression and classification tasks.
result Deep overparameterized neural networks are statistically consistent across different tasks when regularization is applied.
Recent studies show overparameterized neural networks behave like convex systems.
problem Understanding the behavior of overparameterized neural networks.
method Analysis of two-layer neural networks, focusing on restricted settings and neural tangent kernel space.
result Overparameterized neural networks behave like convex systems under certain conditions.
Our work proves convergence to low robust training loss for polynomial width ReLU networks.
problem Understanding why adversarial training leads to low robust training loss in over-parameterized neural nets.
method Extending convergence theory for standard supervised training to adversarial training, using tools from online learning and showing ReLU networks can approximate the step function.
result Convergence to low robust training loss for polynomial width ReLU networks under natural assumptions.
Overparameterized ensembles don't offer generalization benefits over single large models.
problem Theoretical limitations of ensembles in overparameterized settings.
method Using ensembles of random feature (RF) regressors, the paper clarifies how modern ensembles differ from underparameterized counterparts.
result Infinite ensembles of overparameterized RF regressors become pointwise equivalent to single infinite-width RF regressors, and finite width ensembles converge to single models with the same parameter budget.
Estimates generalization gap for overparameterized models using Langevin approximation.
problem Estimating the difference between training and generalization performance in overparameterized models.
method Functional variance and Langevin approximation of functional variance.
result Demonstrates efficient estimation of generalization gaps for overparameterized models.
Study shows overparameterization helps shallow neural networks recover signals in high dimensions.
problem Signal recovery in shallow neural networks with overparameterization.
method Gradient flow on population risk, Gaussian distribution assumption, high-dimensional limit analysis.
result Minimal overparameterization is sufficient for strong recovery of signals.
Overparameterization enhances SAM's effectiveness in minimizing sharpness.
problem Improving generalization in deep neural networks.
method Analysis of Sharpness-Aware Minimization (SAM) under varying degrees of overparameterization.
result Overparameterization significantly improves SAM's performance, particularly in noisy and sparse settings.
Overparameterized models improve performance in sequential learning tasks.
problem Catastrophic forgetting in overparameterized neural networks.
method Two-task linear regression problem with random orthogonal transformations.
result Overparameterization mitigates catastrophic forgetting in sequential learning tasks.
This study explains how different training methods affect the minimizer of neural networks.
problem How training methods influence the minimizer of neural networks.
method Explains how initialization size, adaptive optimization (AdaGrad), and stochastic mini-batch training affect the minimizer.
result Different training methods lead to different minimizers, even in overparameterized networks.
This work shows neural networks can solve non-convex constraints problems.
problem Training neural networks under non-convex constraints.
method Project stochastic gradient descent with no-regret analysis of online learning.
result Overparameterized neural networks achieve near-optimal and near-feasible solutions.
The paper examines VI for overparameterized BNNs, revealing a trade-off between likelihood and KL terms.
problem Critical issue in mean-field VI training for overparameterized BNNs.
method Theoretical and empirical study of overparameterized two-layer BNNs using VI.
result A trade-off between likelihood and KL terms in overparameterized regime, with KL scaling crucial.
New loss function restores importance weighting in overparameterized models.
problem Restoring importance weighting in overparameterized neural networks.
method Introduced polynomially-tailed losses to restore effects of importance weighting.
result Polynomially-tailed losses improve performance in correcting distribution shift.
Study shows DNNs can recover functions with fewer samples than model parameters at overparameterization.
problem Determining reliable function recovery in overparameterized deep neural networks.
method Introducing 'local linear recovery' (LLR) and proving upper bounds on sample sizes for recovery.
result Upper bounds on optimistic sample sizes for function recovery in overparameterized DNNs are achieved.
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.
Our paper examines binary linear classification under Gaussian mixtures, revealing conditions for optimal performance.
problem Understanding the conditions for optimal performance of binary linear classifiers under Gaussian mixtures.
method We study max-margin SVM and min-norm interpolating classifiers, deriving bounds and conditions for optimal performance.
result Interpolating estimators achieve asymptotically optimal performance under certain conditions, emphasizing the role of SNR and covariance.
Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class classification via stochastic gradient descent (SGD) from random initialization. In …
Study on SGD for overparameterized neural networks, focusing on convergence rates.
problem Understanding convergence rates of SGD in overparameterized two-layer neural networks.
method Combines NTK approximation with RKHS analysis to explore SGD dynamics.
result Established sharp convergence rates for SGD in overparameterized two-layer neural networks.
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.
Sigmoid autoencoders can implement associative memory with certain conditions.
problem Implementing associative memory in neural networks.
method Theoretical analysis of overparameterized sigmoid autoencoders using the NTK and iterative maps.
result Overparameterized sigmoid autoencoders can have attractors in the NTK limit, leading to associative memory.
We theoretically study the landscape of the training error for neural networks in overparameterized cases. We consider three basic methods for embedding a network into a wider one with more hidden units, and discuss whether a minimum point of the narrower network gives a minimum or saddle point of the wider one. Our re…
Deep neural networks perform well on local tasks but struggle with global tasks.
problem Understanding the limitations of overparameterized deep neural networks in learning global functions.
method Introduced k-local and k-global functions to study the interplay between depth and function locality. result Depth is beneficial for learning local functions but detrimental to learning global functions.
The study examines deep convolutional neural networks and their learning ability.
problem Understanding the learning ability of deep convolutional neural networks (DCNNs).
method Examines DCNNs under both underparameterized and overparameterized settings, using a novel network deepening scheme.
result Establishes the first learning rates of underparameterized DCNNs and shows how adding layers can create interpolating DCNNs with good learning rates.
Jiang et al. (2020) found no uniformly tight generalization bounds for neural networks in the overparameterized setting.
problem Finding uniformly tight generalization bounds for neural networks in the overparameterized setting.
method Examined more than a dozen generalization bounds, proving that no bounds can be uniformly tight in the overparameterized setting.
result No generalization bounds can be uniformly tight in the overparameterized setting.
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this work, we prove that overparameterized neural networks can learn some notable concept classes, including…
Study on neural network dynamics in high dimensions with quadratic activation.
problem Understanding training dynamics in overparameterized neural networks.
method Derivation of gradient flow equations and analysis under l2-regularization.
result Characterization of estimator performance and spectral properties in the high-dimensional limit.
Stochastic gradient descent (SGD) forms the core optimization method for deep neural networks. While some theoretical progress has been made, it still remains unclear why SGD leads the learning dynamics in overparameterized networks to solutions that generalize well. Here we show that for overparameterized networks wit…
This work challenges the Neural Tangent Kernel's role in overparameterized neural networks, especially with large width and depth.
problem The Neural Tangent Kernel's behavior in overparameterized neural networks with large width and depth is unclear.
method Experimental and theoretical analysis of ReLU networks with large width and depth.
result The aggregate norm of hidden neuron deviations does not vanish in infinitely-wide ReLU networks, indicating non-trivial behavior.
Deeper networks are better for local labels, but shallower for global labels.
problem Understanding the effect of depth in overparameterized neural networks.
method Introduced local and global labels to investigate the advantage of depth.
result Deeper networks are better for local labels, shallower for global labels.
The paper analyzes stability and generalization of shallow neural networks using gradient methods.
problem Understanding the generalization of overparameterized shallow neural networks.
method The paper uses gradient descent and stochastic gradient descent to study shallow neural networks, developing consistent excess risk bounds.
result The analysis improves on existing methods by providing a refined estimation of iterates and Hessian eigenvalues, leading to better excess risk bounds.
Overparameterization aids in model pruning, leading to improved test accuracy.
problem Improving lightweight model performance through pruning.
method Theoretical analysis and high-dimensional asymptotics of model pruning in overparameterized neural networks.
result Even with known informative features, training a large model and then pruning leads to better test accuracy.
Gradient descent converges linearly for overparameterized linear networks.
problem Convergence of gradient descent for overparameterized neural networks.
method Local Polyak-Lojasiewicz and Descent Lemma for overparameterized linear models.
result Gradient descent achieves linear convergence for two-layer linear networks under relaxed assumptions.
Study of infinitely deep but narrow neural networks using NTK theory.
problem Analyzing the role of depth in deep learning with overparameterized networks.
method Infinite-depth limit analysis of MLP and CNN using Neural Tangent Kernel (NTK) theory.
result Established trainability guarantee for infinitely deep but narrow neural networks.
The paper analyzes how gradient descent implicitly regularizes solutions in overparameterized neural networks, revealing depth-dependent regularization effects.
problem Understanding implicit regularization in overparameterized linear neural networks for regression problems.
method Analyzing the approximation error between gradient flow limit points and ℓ1-minimization solutions, deriving tight upper and lower bounds. result The approximation error decreases linearly for D≥3 and at a slower rate for D=2, linked to null space property constants.