Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

22446688 · Jun 202019922001200920172026
48 results for Lipschitz widths

This paper studies bounds for the Lipschitz constant of random neural networks.

problem Quantifying the worst-case robustness of neural networks against adversarial perturbations.
method Analyzes upper and lower bounds for the Lipschitz constant of random ReLU neural networks under specific initialization conditions.
result For deep networks, the upper bound is larger than the lower bound by a logarithmic factor in width.

Improved neural network depth-width trade-offs via dynamical systems.

problem Expressivity of neural networks in terms of depth and width.
method Connection with dynamical systems, focusing on periodic points and Lipschitz constants.
result Sharper width lower bounds for neural networks, yielding exponential depth-width separations.

Study shows limits on deep and shallow neural networks for approximating compact sets.

problem Understanding the limitations of deep and shallow neural networks in approximating compact sets.
method Proved Carl's type inequalities for approximation error, using Lipschitz widths.
result Lower bounds on approximation error for neural network outputs.

The paper studies Lipschitz bounds for integral kernels under differentiability assumptions.

problem Understanding the Lipschitz continuity of feature maps associated with integral kernels.
method Analyzes differentiability assumptions to derive explicit formulas for Lipschitz constants and conditions for non-Lipschitz continuity.
result Explicit formulas and conditions for Lipschitz continuity of feature maps associated with various kernels.

New optimizers control network width scaling, improving stability and transfer across different model sizes.

problem Designing stable optimizers for networks of varying widths.
method Interpreting optimizers as steepest descent under mean-normalized operator norms, enabling layerwise composability and width-independent bounds.
result New optimizers like row normalization and column normalization provide stable learning-rate transfer across different model widths.

Wide deep neural networks with Gaussian weights approximate Gaussian processes closely.

problem Understanding the approximation of deep neural networks with Gaussian weights to Gaussian processes.
method Established novel rates for the Gaussian approximation of random deep neural networks with Gaussian parameters and Lipschitz activation functions in the wide limit.
result The distance between the network output and the Gaussian approximation scales inversely with the width of the network.

This paper optimizes ReLU networks for approximating Hölder continuous functions.

problem Optimizing the approximation rate of ReLU networks in terms of width and depth.
method Constructive proof of ReLU networks' approximation power with specific width and depth constraints.
result Optimal approximation rate of ReLU networks with width and depth constraints.

Proves a quantitative index theorem for positive scalar curvature metrics.

problem Studying conjectures and open questions on positive scalar curvature.
method Quantitative relative index theorem and λλ-Lipschitz rigidity theorem.
result Positive answers to Gromov's open questions on scalar curvature.

Poor approximators found in neural networks and random feature models.

problem Understanding why certain neural networks and models perform poorly in approximating functions.
method Established a scale separation of Kolmogorov width type and applied it to neural networks and random feature models.
result Reproducing kernel Hilbert spaces and two-layer neural networks are poor L2L^2-approximators for certain functions.

Study Gaussian approximation for deep neural networks with random weights.

problem Understanding the distribution of deep neural networks with random weights.
method Established Gaussian approximation bounds in Wasserstein-1 norm.
result Convergence rates of order n(1/6)L1+εn^{-({1}/{6})^{L-1} + ε} for deep networks with proportional layer widths.

This work analyzes how deep neural networks' expressiveness increases with depth and width.

problem Understanding the expressiveness of deep neural networks (DNNs) based on their Lipschitz constants.
method Leveraging random matrix theory, the study characterizes the expressiveness of DNNs by their Lipschitz constant, showing exponential and polynomial increases with depth and width, respectively.
result The expressiveness of DNNs increases exponentially with depth and polynomially with width, consistent with function approximation benefits.

This paper analyzes the Lipschitz constants of deep neural networks with random weights.

problem Estimating the Lipschitz constants of deep neural networks with random parameters.
method High probability upper and lower bounds derived for ReLU neural networks with He initialization.
result The behavior of the Lipschitz constant varies significantly between p[1,2)p \in [1,2) and p[2,]p \in [2,\infty].

Gradient descent converges linearly in finite-width networks with positive NTK and compatible conditions.

problem Local convergence of gradient descent in finite-width networks.
method Positive Neural Tangent Kernel (NTK), local Polyak-Łojasiewicz inequality, fixed-step containment in Locally Quasi-Convex Region (LQCR).
result Linear convergence achieved under specific conditions.

In \cite{GrOrang}, Gromov asks the following question: given a nullhomotopic map f:SmSnf:S^m \to S^n of Lipschitz constant LL, how does the Lipschitz constant of an optimal nullhomotopy of ff depend on LL, mm, and nn? We establish that for fixed mm and nn, the answer is at worst quadratic in LL. More precisely, we …

2016-11-10abs ↗pdf ↗

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.

Two-layer neural networks must be robust, even with arbitrary weights.

problem Proving the robustness of two-layer neural networks with arbitrary weights.
method Developed a new function-space covering method to prove the robustness law, replacing parameter-space covering.
result Proved the conjectured law for two-layer networks with arbitrary real weights, biases, and affine skip connections.

We prove bounds on the generalization error of convolutional networks. The bounds are in terms of the training loss, the number of parameters, the Lipschitz constant of the loss and the distance from the weights to the initial weights. They are independent of the number of pixels in the input, and the height and width …

2019-05-29abs ↗pdf ↗

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.

This paper tightens bounds on the smallest eigenvalue of NTK for deep ReLU networks.

problem Analyzing the smallest eigenvalue of Neural Tangent Kernel for deep ReLU networks.
method Analyzing various quantities of independent interest, including lower bounds on the smallest singular value of hidden feature matrices and upper bounds on the Lipschitz constant of input-output feature maps.
result Tight bounds on the smallest eigenvalue of NTK matrices for deep ReLU nets, both in the limiting case of infinite widths and for finite widths.

Wider networks improve natural accuracy but worsen perturbation stability, affecting overall robustness.

problem Understanding the tradeoff between natural accuracy and perturbation stability in wider neural networks for adversarial robustness.
method Careful examination of the relationship between network width, robust regularization parameter λ, and perturbation stability using neural tangent kernels.
result Wider networks can achieve better natural accuracy but worse perturbation stability, leading to potentially worse overall model robustness.

Gradient descent proves global convergence for deep networks with a single wide layer.

problem Proving global convergence of gradient descent for deep ReLU networks.
method Simplified proof using a single wide layer, leveraging ReLU's Lipschitz property.
result Gradient descent converges globally for networks with a single wide layer.

The paper analyzes GD for KANs, deriving bounds for training, generalization, and privacy.

problem Training dynamics, generalization, and privacy properties of KANs.
method Gradient Descent (GD) analysis for two-layer KANs under logistic loss and NTK-separable assumption.
result Polylogarithmic width suffices for GD to achieve optimization and generalization rates under DP.

This paper analyzes convergence of large-scale Transformers with weight decay.

problem Understanding optimization guarantees in large-scale Transformer training.
method Construct mean-field limit, show gradient flow convergence to PDE, demonstrate global minimum consistency.
result Gradient flow reaches global minimum in large-scale Transformers with small weight decay.

This paper analyzes SHAP values using Fourier expansions for model interpretability.

problem Understanding and interpreting SHAP values in complex models.
method Developed a spectral framework using Fourier expansions for SHAP values in various model regimes.
result SHAP values are Lipschitz continuous in the deterministic regime and converge to Gaussian process values in the probabilistic regime.

Bounds on Gaussian approximation for neural networks with novel smoothing techniques.

problem Approximating the distribution of wide random neural networks.
method Stein's method, Gaussian smoothing, Laplacian operators, Cameron-Martin space.
result First bounds on Gaussian approximation of wide random neural networks.

Empirical study compares finite- and infinite-width BNNs, revealing performance differences under model mismatch.

problem Comparing BNNs with different widths due to conflicting model properties and inference intractability.
method Empirical comparison of finite- and infinite-width BNNs, analyzing performance under model mismatch.
result Increasing width can hurt BNN performance when the model is mis-specified, and finite-width BNNs generalize better under model mismatch.

Lectures on deep learning properties in infinite and large-width networks.

problem Understanding deep neural networks in extreme width conditions.
method Analysis of random deep neural networks, connections to linear models, kernels, and Gaussian processes, perturbative and non-perturbative treatments.
result Properties and behaviors of deep neural networks in the infinite-width limit and large-width regime.

A number of results for C2^2-smooth surfaces of constant width in Euclidean 3-space E3{\mathbb{E}}^3 are obtained. In particular, an integral inequality for constant width surfaces is established. This is used to prove that the ratio of volume to cubed width of a constant width surface is reduced by shrinking it along…

2007-04-24abs ↗pdf ↗

The paper improves methods for generating prediction intervals in regression.

problem Uncertainty quantification in regression models.
method Formalizes prediction interval generation as an optimization problem, studying generalization and calibration.
result Empirical demonstration of improved testing performances compared to existing methods.

The paper extends the collar theorem to non-compact surfaces using new comparison theorems.

problem Proving the collar theorem for non-compact surfaces.
method Developed new Toponogov-type triangle comparison theorems.
result Eliminated the compactness hypothesis for the collar theorem.