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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Random neural networks”

A generative neural network model for random dot product graphsstat.ML

GraphMoE generates random graphs using neural networks and graphlets.

problem Learning generative models for random graphs.

method GraphMoE uses a neural network trained with graphlets and subgraph counts to match the distribution of random graphs.

result GraphMoE can generate graphs that mimic various real-world datasets and fool graph classifiers.

neural networks random graphs graphlets subgraph counts generative models

2022-04-15abs ↗pdf ↗

A Correspondence Between Random Neural Networks and Statistical Field Theorystat.ML

A number of recent papers have provided evidence that practical design questions about neural networks may be tackled theoretically by studying the behavior of random networks. However, until now the tools available for analyzing random neural networks have been relatively ad-hoc. In this work, we show that the distrib…

2017-10-18abs ↗pdf ↗

Random feature neural networks learn Black-Scholes type PDEs without curse of dimensionalitycs.LG

Random neural nets learn Black-Scholes PDEs without dimensionality issues.

problem Learning Black-Scholes type PDEs efficiently in high dimensions.

method Random feature neural networks applied to Kolmogorov PDEs.

result Random neural nets avoid the curse of dimensionality for Black-Scholes PDEs.

Black-Scholes PDEs Random neural nets Curse of dimensionality Kolmogorov PDEs

2021-06-14abs ↗pdf ↗

Neural Tangent Kernels and Fisher Information Matrices for Simple ReLU Networks with Random Hidden Weightscs.LG

The study examines Fisher information matrices and neural tangent kernels for simple ReLU networks with random weights.

problem Understanding the relationship between Fisher information matrices and neural tangent kernels for 2-layer ReLU networks.

method Analyzes Fisher information matrices and neural tangent kernels for 2-layer ReLU networks with random hidden weights, focusing on spectral decomposition and eigenfunctions.

result Obtained an approximation formula for functions represented by 2-layer neural networks.

Fisher information neural tangent kernels ReLU networks random weights spectral decomposition

2025-07-24abs ↗pdf ↗

A single gradient step finds adversarial examples on random two-layers neural networkscs.LG

Single gradient step finds adversarial examples in random neural networks.

problem Finding adversarial examples in neural networks with random architectures.

method Gradient descent approach applied to random undercomplete and overcomplete two-layers neural networks.

result A single gradient step is sufficient to find adversarial examples in random neural networks.

adversarial examples gradient descent random neural networks undercomplete overcomplete

2021-04-08abs ↗pdf ↗

Deep Randomized Neural Networkscs.LG

Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network architectures where the connections to the hidden layer(s) are left untrained after i…

2020-02-27abs ↗pdf ↗

G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networkscs.LG

G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.

problem Creating high-accuracy binary neural networks with theoretical guarantees.

method Proposes a novel floating-point G-Net family with randomized binary embeddings and theoretical accuracy guarantees.

result Empirically, G-Net achieves almost 30% higher accuracy on CIFAR-10 compared to prior HDC models.

binary neural networks randomized algorithms hyperdimensional computing concentration of measure CIFAR-10

2025-11-26abs ↗pdf ↗

What Do Neural Networks Learn When Trained With Random Labels?stat.ML

Neural networks learn patterns in random data, improving downstream performance.

problem Understanding what deep networks learn with random labels.

method Analytical and empirical study of convolutional and fully connected networks pre-trained on random labels.

result Pre-trained networks on random labels transfer faster to real datasets, despite specialization effects.

neural networks random labels principal components positive transfer CIFAR10

2020-06-18abs ↗pdf ↗

Knots in random neural networksstat.ML

The weights of a neural network are typically initialized at random, and one can think of the functions produced by such a network as having been generated by a prior over some function space. Studying random networks, then, is useful for a Bayesian understanding of the network evolution in early stages of training. In…

2018-11-27abs ↗pdf ↗

On the relationship between multivariate splines and infinitely-wide neural networkscs.LG

Multivariate splines linked to infinitely-wide neural networks with improved numerical performance.

problem Understanding the relationship between multivariate splines and neural networks.

method Showed multivariate splines can be represented as random features in infinitely-wide neural networks with a homogeneous activation function.

result The function space of multivariate splines is a Sobolev space on a Euclidean ball with explicit norm bounds on derivatives.

multivariate splines neural networks random features Sobolev space rectified linear unit

2023-02-07abs ↗pdf ↗

Upper and lower bounds for the Lipschitz constant of random neural networksstat.ML

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.

Lipschitz constant neural networks adversarial examples ReLU networks random initialization

2023-11-02abs ↗pdf ↗

Universal Time-Uniform Trajectory Approximation for Random Dynamical Systems with Recurrent Neural Networkscs.NE

Deep neural nets approximate random dynamical system trajectories uniformly in time.

problem Approximating trajectories of random dynamical systems over infinite time horizons.

method Recurrent neural networks with simple feedback structures.

result Certain random trajectories can be approximated uniformly in time to any desired accuracy.

Recurrent neural networks Random dynamical systems Uniform approximation Deep learning Trajectory approximation

2022-11-15abs ↗pdf ↗

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?cs.LG

Bandlimited random neural networks may not approximate all functions perfectly.

problem Expressive power of shallow neural networks with bandlimited random weights.

method Ridgelet analysis for deriving approximation error lower bounds.

result Bandlimited random weights can lead to non-zero approximation error.

Neural Networks Universal Approximation Bandlimited Weights Ridgelet Analysis Approximation Error

2020-08-19abs ↗pdf ↗

Universal approximation property of Banach space-valued random feature models including random neural networkscs.LG

Random feature models approximate functions in Banach spaces efficiently.

problem Approximating functions in Banach spaces efficiently.

method Randomly initialized feature maps and linear readout training.

result Universal approximation in Bochner spaces for Banach space-valued models.

random feature models Banach spaces universal approximation machine learning random neural networks

2023-12-13abs ↗pdf ↗

Random matrix analysis of deep neural network weight matricescond-mat.dis-nn

Random matrix analysis reveals that neural network weights are mostly random, with some indicating learned information.

problem Understanding how neural networks store information needed for tasks.

method Random matrix theory (RMT) applied to weight matrices of trained deep neural networks.

result Most singular values and eigenvectors of trained neural networks follow universal RMT predictions, suggesting they are random and do not contain system-specific information.

deep neural networks random matrix theory singular values eigenvectors neural network weights

2022-03-28abs ↗pdf ↗

Improving Neural Network Training in Low Dimensional Random Basescs.LG

Improved neural network training in low-dimensional random bases.

problem Inefficient optimization in large-scale neural networks.

method Re-draw random subspace at each training step, apply independent projections to different network parts.

result Significantly better optimization performance and efficiency.

neural networks stochastic gradient descent random projections hardware acceleration subspace optimization

2020-11-09abs ↗pdf ↗

Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networkscs.LG

Bounds neural network output distribution to Gaussian for random initialization.

problem Quantifying the distribution of randomly initialized deep neural networks.

method Quantitative Gaussian approximation using quadratic Wasserstein distance.

result Explicit inequalities show how network sizes affect Gaussian behavior.

deep learning neural networks Gaussian approximation random initialization Wasserstein distance

2022-03-14abs ↗pdf ↗

Adversarial Robustness Guarantees for Random Deep Neural Networksstat.ML

Random deep neural networks are robust to adversarial examples, scaling with input size and dimension.

problem Adversarial examples challenge the reliability of deep learning algorithms.

method Analysis of random deep neural networks with Gaussian process equivalence and experiments on MNIST and CIFAR10.

result The

\ell^p

distance of adversarial examples scales as

1/\sqrt{d} imes \ell^p

norm of the input.

adversarial robustness random neural networks Gaussian processes MNIST CIFAR10

2020-04-13abs ↗pdf ↗

On the Impacts of the Random Initialization in the Neural Tangent Kernel Theorystat.ML

This paper examines the impact of random initialization in neural networks using NTK theory.

problem Understanding the impact of random initialization in neural networks using NTK theory.

method Analyzes the convergence of training dynamics and generalization error of wide neural networks with random initialization.

result The generalization error of wide neural networks trained by gradient descent is \( \Omega(n^{-\frac{3}{d+3}}) \), highlighting the benefits of mirror initialization and suggesting limitations of NTK theory.

random initialization neural tangent kernel generalization error neural networks curse of dimensionality

2024-10-08abs ↗pdf ↗

Neural Random Forest Imitationcs.LG

We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks. Existing methods propose a direct mapping and produce very inefficient architectures. In this work, we introduce an imitation learning approach by generating training data from a random forest and learning…

2019-11-25abs ↗pdf ↗

Most Neural Networks Are Almost Learnablecs.LG

New algorithm learns random neural networks efficiently.

problem Learning random constant-depth neural networks efficiently.

method Presented a PTAS (Polynomial-Time Approximation Scheme) for learning random Xavier networks of fixed depth.

result For any fixed ε and depth i, there is a poly-time algorithm that learns random Xavier networks up to an additive error of ε.

Neural Networks Learning Algorithms Random Networks Polynomial-Time Approximation Scheme Constant Depth

2023-05-25abs ↗pdf ↗

Epistemic Deep Learningcs.LG

Introduces epistemic deep learning for better uncertainty estimation in neural networks.

problem Uncertainty quantification in deep neural networks.

method Random-set convolutional neural networks with belief function-based loss functions.

result Epistemic approach produces better performance in uncertainty estimation.

deep learning uncertainty quantification belief functions random sets neural networks

2022-06-15abs ↗pdf ↗

Probabilistic Inference of Binary Markov Random Fields in Spiking Neural Networks through Mean-field Approximationq-bio.NC

Recent studies have suggested that the cognitive process of the human brain is realized as probabilistic inference and can be further modeled by probabilistic graphical models like Markov random fields. Nevertheless, it remains unclear how probabilistic inference can be implemented by a network of spiking neurons in th…

2019-02-22abs ↗pdf ↗

Universal Approximation in Dropout Neural Networkscs.LG

Dropout neural networks can approximate any function with high probability.

problem Approximating functions with dropout neural networks.

method Two universal approximation theorems for dropout neural networks in random and deterministic modes.

result Dropout neural networks can approximate any function in probability and in

L^q

dropout neural networks universal approximation probability random filters

2020-12-18abs ↗pdf ↗

Pruning Randomly Initialized Neural Networks with Iterative Randomizationcs.LG

A new method to prune neural networks with iterative randomization improves efficiency.

problem Efficiency in pruning randomly initialized neural networks.

method Iteratively randomizing weight values to reduce parameter requirements.

result The method achieves remarkable performance with fewer parameters.

neural networks pruning randomization parameter efficiency lottery ticket hypothesis

2021-06-17abs ↗pdf ↗

Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?cs.LG

New method shows random, diverse initializations are not essential for deep neural networks.

problem The necessity of random, diverse initializations in deep neural networks.

method Constructed a deep convolutional network with identical features by initializing weights to 0, enabling signal propagation and stable gradients.

result Random, diverse initializations are not necessary for training neural networks.

deep neural networks initialization signal propagation feature diversity random weights

2020-07-02abs ↗pdf ↗

On the effects of biased quantum random numbers on the initialization of artificial neural networksquant-ph

Study finds no significant difference in neural network weights with quantum random numbers.

problem Effects of biased quantum random numbers on neural network initialization.

method Empirical study using quantum hardware and classical pseudo-random numbers.

result No statistically significant difference found between quantum random numbers and other types.

quantum computing machine learning random numbers neural networks quantum hardware

2021-08-30abs ↗pdf ↗

Randomized Neural Networks for estimation of exposure profiles and Credit Valuation Adjustment (CVA) for American Equity Optionsq-fin.CP

Randomized neural networks improve exposure and CVA estimation for American options.

problem Estimation of exposure and CVA for American options

method Randomized neural networks

result Improves convergence and efficiency in high-dimensional problems

randomized neural networks exposure CVA American options Monte Carlo

2026-06-23abs ↗pdf ↗

Representing Random Utility Choice Models with Neural Networkscs.LG

Neural networks approximate random utility models for choice prediction.

problem Approximating random utility models with neural networks.

method RUMnets, a neural network-based model inspired by RUM framework.

result RUMnets can approximate any RUM model arbitrarily closely and vice versa.

Neural Networks Random Utility Models Choice Prediction Discrete Choice Deep Learning

2022-07-26abs ↗pdf ↗

On Random Matrices Arising in Deep Neural Networks: General I.I.D. Casemath-ph

Study on random matrices in deep neural networks with IID entries.

problem Distribution of singular values in product of random matrices for deep neural networks.

method Random matrix theory with a streamlined approach for non-Gaussian data.

result Generalization of macroscopic universality property to non-Gaussian data.

random matrices deep neural networks singular values IID entries macroscopic universality

2020-11-20abs ↗pdf ↗

On the Universality of Graph Neural Networks on Large Random Graphsstat.ML

Graph Neural Networks struggle on random graphs without node identifiers.

problem Graph Neural Networks' limitations on random graphs without node identifiers.

method Study of Graph Neural Networks and Structural Graph Neural Networks convergence on large random graphs.

result Structural Graph Neural Networks are more powerful and universal than Graph Neural Networks on random graphs.

Graph Neural Networks Random Graphs Structural Graph Neural Networks Universality Stochastic Block Model

2021-05-27abs ↗pdf ↗

Expressivity of Neural Networks with Random Weights and Learned Biasescs.NE

Neural networks with learned biases can approximate any function.

problem Whether neural networks with only learned biases can approximate any continuous function.

method Theoretical and numerical analysis of random weights and learned biases in neural networks.

result Feedforward and recurrent neural networks with random weights can approximate any continuous function and dynamical systems.

neural networks universal approximation random weights learned biases neuroscience

2024-07-01abs ↗pdf ↗

Stochastic gradient descent with random learning ratecs.LG

Random learning rate improves neural network training without extra cost.

problem Optimizing neural networks with stochastic gradient descent.

method Uniformly-distributed random learning rate in SGD.

result Random learning rate yields better regularization without extra computational cost.

neural networks stochastic gradient descent random learning rate Fokker-Planck temperature

2020-03-15abs ↗pdf ↗

Infinite-width limit of deep linear neural networkscs.LG

The paper examines how deep linear neural networks behave as they become infinitely wide.

problem Understanding the behavior of deep linear neural networks as they approach infinite width.

method Analyzes the infinite-width limit of deep linear neural networks, proving convergence to deterministic models and providing precise laws for random weights.

result The training dynamics of deep linear neural networks converge to those of a deterministic model, and the weights' behavior is precisely described.

deep learning neural networks infinite width gradient descent random weights

2022-11-29abs ↗pdf ↗

Deep Random Projection Outlyingness for Unsupervised Anomaly Detectioneess.SP

Modified neural network enhances unsupervised anomaly detection.

problem Unsupervised anomaly detection in multimodal data.

method Neural network with modified random projection outlyingness.

result Performance comparable to state-of-the-art methods.

anomaly detection unsupervised learning random projection neural networks

2021-06-08abs ↗pdf ↗

Random Vector Functional Link Networks for Function Approximation on Manifoldsstat.ML

Randomized neural networks improve function approximation on manifolds.

problem Slow learning in neural networks on manifolds.

method Random vector functional link networks for function approximation.

result Theoretical guarantees for function approximation on manifolds with high probability.

neural networks function approximation manifolds randomization universal approximator

2020-07-30abs ↗pdf ↗

Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernelsmath.FA

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

L^2

-approximators for certain functions.

Kolmogorov width reproducing kernel Hilbert spaces two-layer neural networks random feature models approximation theory

2020-05-21abs ↗pdf ↗

Cross-Validation and Uncertainty Determination for Randomized Neural Networks with Applications to Mobile Sensorsstat.ML

Study improves prediction accuracy and uncertainty for mobile sensor data using randomized neural networks.

problem Improving prediction accuracy and uncertainty for mobile sensor data.

method Cross-validation and uncertainty determination for randomized neural networks.

result Improved out-of-sample performance and confidence intervals for prediction error.

randomized neural networks cross-validation uncertainty determination mobile sensors prediction error

2021-01-06abs ↗pdf ↗

Deep Learning without Global Optimization by Random Fourier Neural Networkscs.LG

New algorithm trains deep neural networks without global optimization.

problem Training deep neural networks efficiently and without global optimization.

method Uses random complex exponential activation functions and Markov Chain Monte Carlo sampling.

result Consistently attains theoretical approximation rate for residual networks.

Deep Learning Random Fourier Neural Networks Markov Chain Monte Carlo Complex Exponential Activation Gibbs Phenomena

2024-07-16abs ↗pdf ↗

Six Lectures on Linearized Neural Networksstat.ML

Analyzes neural networks using linear models to understand their behavior.

problem Understanding multi-layer neural networks through linear models.

method Recalls and reviews four models: linear regression with concentrated features, kernel ridge regression, random feature model, and neural tangent model.

result Highlights limitations of linear theory and discusses approaches to overcome them.

neural networks linear models lazy regime linear regression kernel ridge regression

2023-08-25abs ↗pdf ↗

Gaussian random field approximation via Stein's method with applications to wide random neural networksmath.PR

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.

Stein's method Gaussian smoothing Random neural networks Wasserstein distance Wide networks

2023-06-28abs ↗pdf ↗

Appearance of Random Matrix Theory in Deep Learningcs.LG

Random Matrix Theory explains loss surface Hessians in neural networks.

problem Understanding the loss surfaces of neural networks.

method Investigation of local spectral statistics of neural network Hessians.

result Excellent agreement with Gaussian Orthogonal Ensemble statistics.

Random Matrix Theory Neural Networks Loss Surface Hessian Gaussian Orthogonal Ensemble

2021-02-12abs ↗pdf ↗

Enhanced Expressive Power and Fast Training of Neural Networks by Random Projectionscs.LG

Random projections are able to perform dimension reduction efficiently for datasets with nonlinear low-dimensional structures. One well-known example is that random matrices embed sparse vectors into a low-dimensional subspace nearly isometrically, known as the restricted isometric property in compressed sensing. In th…

2018-11-22abs ↗pdf ↗

Adversarial Examples Detection with Bayesian Neural Networkstat.ML

Proposes BATer for improved adversarial example detection.

problem Detecting adversarial examples in neural networks.

method Introduces a Bayesian adversarial example detector (BATer) using random components in a Bayesian neural network.

result BATer outperforms state-of-the-art detectors in adversarial example detection.

adversarial examples Bayesian neural network random components distributional difference hidden layer output

2021-05-18abs ↗pdf ↗

Neural Random Forestsstat.ML

Given an ensemble of randomized regression trees, it is possible to restructure them as a collection of multilayered neural networks with particular connection weights. Following this principle, we reformulate the random forest method of Breiman (2001) into a neural network setting, and in turn propose two new hybrid p…

2016-04-25abs ↗pdf ↗

Randomly Initialized One-Layer Neural Networks Make Data Linearly Separablecs.LG

Randomly initialized neural networks can linearly separate arbitrary sets.

problem Mapping two arbitrary sets to linearly separable sets.

method Randomly initialized one-layer neural networks with sufficient width.

result With high probability, these networks can transform two sets into linearly separable sets.

neural networks one-layer networks linear separability random initialization concentration of random matrices

2022-05-24abs ↗pdf ↗

Analyzing Neural Networks Based on Random Graphscs.LG

We perform a massive evaluation of neural networks with architectures corresponding to random graphs of various types. We investigate various structural and numerical properties of the graphs in relation to neural network test accuracy. We find that none of the classical numerical graph invariants by itself allows to s…

2020-02-19abs ↗pdf ↗

Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networkscs.LG

Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs). NTK theory leads to concrete convergence and generalization results, yet the empirical performance of neural networks are observed to exceed their linearized …

2019-10-03abs ↗pdf ↗