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

count % of corpus

48 results for “network sampling”

Training Guarantees of Neural Network Classification Two-Sample Tests by Kernel Analysisstat.ML

The paper analyzes a neural network two-sample test using kernel analysis.

problem Determining if two datasets come from the same distribution.

method Time-analysis on a neural tangent kernel (NTK) two-sample test, extending to realistic neural network dynamics.

result Training times needed to detect deviations are well-separated in null and alternative hypothesis scenarios.

neural network two-sample test kernel analysis time-analysis neural tangent kernel

2024-07-05abs ↗pdf ↗

Network Sampling: From Static to Streaming Graphscs.SI

Network sampling is integral to the analysis of social, information, and biological networks. Since many real-world networks are massive in size, continuously evolving, and/or distributed in nature, the network structure is often sampled in order to facilitate study. For these reasons, a more thorough and complete unde…

2012-11-14abs ↗pdf ↗

Test Sample Accuracy Scales with Training Sample Density in Neural Networkscs.LG

Neural network accuracy improves with denser training samples.

problem Improving neural network accuracy on unseen test samples.

method Bounding empirical training error smoothed across activation regions and using it to discard high-risk test samples.

result Discarding high-risk test samples based on error bounds improves prediction accuracy by up to 20%.

neural networks training sample density test sample accuracy representation space activation regions

2021-06-15abs ↗pdf ↗

Fitting Low-rank Models on Egocentrically Sampled Partial Networkscs.SI

New method fits low-rank models for egocentrically sampled networks.

problem Statistical modeling of egocentrically sampled partial networks.

method Graph spectral properties-based approach for low-rank models.

result Consistent recovery of missing subnetworks for sparse networks.

network modeling egocentric sampling low-rank models graph spectral properties link prediction

2023-03-09abs ↗pdf ↗

How many samples are needed to train a deep neural network?math.ST

New study shows neural networks need many samples for training.

problem How much data is needed to train a ReLU feed-forward neural network?

method Theoretical and empirical analysis of ReLU feed-forward neural networks.

result Generalization error scales at

1/\sqrt{n}

in sample size

n

neural networks generalization error ReLU networks sample size

2024-05-26abs ↗pdf ↗

The sampling complexity of learning invertible residual neural networksstat.ML

Residual neural networks don't help overcome sampling complexity issues.

problem Learning invertible residual neural networks from samples is hard due to the curse of dimensionality.

method Investigated invertible residual neural networks and their sampling complexity.

result Invertible residual neural networks still suffer from the curse of dimensionality in sampling complexity.

neural networks residual networks sampling complexity curse of dimensionality invertible networks

2024-11-08abs ↗pdf ↗

Neural Network Approximation of Graph Fourier Transforms for Sparse Sampling of Networked Flow Dynamicscs.LG

Neural networks compress and sample WDN contamination dynamics efficiently.

problem Infrastructure monitoring of complex, networked systems like water distribution networks is expensive and challenging.

method Developed Graph Fourier Transform (GFT) operators and neural networks (NN) for efficient data collection and inference.

result High accuracy reconstruction of contamination dynamics using only 5-10% of the sample set.

Graph Fourier Transform Neural Networks Water Distribution Networks Infrastructure Monitoring Contamination Dynamics

2020-02-11abs ↗pdf ↗

Interpretable Network Representation Learning with Principal Component Analysisstat.ML

A new algorithm identifies interpretable network representations via subgraph count statistics.

problem Interpreting network-valued data samples.

method Principal Component Analysis for Networks (PCAN) and its fast sampling-based version (sPCAN).

result The PCAN and sPCAN methods provide informative and discriminatory features for network samples.

network representation learning principal component analysis interpretable learning subgraph count statistics kernel-based random graphs

2021-06-27abs ↗pdf ↗

Compromise-free Bayesian neural networksstat.ML

Bayesian neural networks show good correlation between out-of-sample performance and Bayesian evidence.

problem Improving the out-of-sample performance of Bayesian neural networks.

method Numerical sampling of Bayesian posterior, ensembling over architectures, analysis of evidence vs. model size.

result Good correlation between out-of-sample performance and Bayesian evidence; ensembling improves performance.

Bayesian neural networks nested sampling evidence ReLU activation tanh activation

2020-04-25abs ↗pdf ↗

Neighborhood Sampling Does Not Learn the Same Graph Neural Networkcs.LG

Neighborhood sampling affects graph neural network training outcomes.

problem Understanding the impact of neighborhood sampling on graph neural network training.

method Theoretical analysis using neural tangent kernels and Gaussian processes.

result Posterior covariance differs for different neighborhood sampling approaches, indicating no dominant approach.

graph neural networks neighborhood sampling neural tangent kernels Gaussian processes training dynamics

2025-09-26abs ↗pdf ↗

A function space analysis of finite neural networks with insights from sampling theorycs.LG

This work uses sampling theory to analyze smoothness and error bounds of finite neural networks.

problem Analyzing the function space of finite neural networks and providing error bounds.

method Applying sampling theory to finite neural networks with non-expansive activation functions, considering both deterministic and random sampling.

result Novel error bounds for univariate neural networks under band-limited input assumption, highlighting the advantage of deterministic uniform sampling.

neural networks function space sampling theory error bounds finite width

2020-04-15abs ↗pdf ↗

Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?cs.LG

New method for Bayesian neural networks reduces inference difficulty.

problem Difficulty in sample-based inference for Bayesian neural networks.

method Embracing mode-connectedness to link overparameterization and sampling difficulty.

result Practical guidelines and deep ensemble approach for effective SBI.

Bayesian neural networks sample-based inference mode-connectedness overparameterization sampling difficulty

2024-02-02abs ↗pdf ↗

Professor Forcing: A New Algorithm for Training Recurrent Networksstat.ML

The Teacher Forcing algorithm trains recurrent networks by supplying observed sequence values as inputs during training and using the network's own one-step-ahead predictions to do multi-step sampling. We introduce the Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of th…

2016-10-27abs ↗pdf ↗

On the Validity of Conformal Prediction for Network Data Under Non-Uniform Samplingmath.ST

Validates conformal prediction for network data under non-uniform sampling.

problem Validity of conformal prediction for network data under non-representative sampling.

method Interprets sampling mechanisms as selection rules, studies validity conditional on selection events, uses permutation invariance and joint exchangeability.

result Finite-sample validity of conformal prediction for certain selection events and asymptotic validity for random walk sampling.

conformal prediction network data non-uniform sampling selection rules permutation invariance

2023-06-12abs ↗pdf ↗

Link prediction for egocentrically sampled networksstat.CO

Link prediction in networks is typically accomplished by estimating or ranking the probabilities of edges for all pairs of nodes. In practice, especially for social networks, the data are often collected by egocentric sampling, which means selecting a subset of nodes and recording all of their edges. This sampling mech…

2018-03-12abs ↗pdf ↗

Principal Component Properties of Adversarial Samplescs.LG

New metric detects adversarial samples with high accuracy.

problem Vulnerability of deep neural networks to adversarial samples.

method Analyzed adversarial samples through their contributions to principal components of images.

result Proposed new metric (k,p) point for measuring robustness to adversarial samples.

adversarial samples principal components deep neural networks robustness ImageNet

2019-12-07abs ↗pdf ↗

On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network Posteriorscs.LG

This paper examines the convergence of adaptive sampling methods for Bayesian neural networks.

problem Uncertainty quantification in deep neural networks, especially for medical applications.

method Locally adaptive and scalable diffusion-based sampling methods.

result These methods can have a substantial bias in the distribution they sample, even in the limit of vanishing step sizes.

Bayesian neural networks uncertainty quantification diffusion-based sampling adaptive step sizes Monte Carlo Markov chain

2024-03-13abs ↗pdf ↗

Almost Uniform Sampling From Neural Networkscs.LG

The paper tackles uniform sampling from neural networks efficiently.

problem Uniform sampling from neural network labelings given a sample.

method Polynomial-time algorithm for general neural networks, random walk for single neuron.

result Uniform sampling with high probability for general neural networks, exact uniform sampling for single neuron.

neural networks uniform sampling polynomial time random walk

2019-12-10abs ↗pdf ↗

Towards Optimal Neural Networks: the Role of Sample Splitting in Hyperparameter Selectionstat.ML

The paper explores how splitting data samples influences optimal neural network hyperparameters.

problem Understanding the effectiveness of neural networks and their hyperparameters.

method Investigates the role of sample splitting in neural network hyperparameter selection.

result Optimal hyperparameters derived from sample splitting lead to a neural network model that minimizes prediction risk asymptotically.

neural networks hyperparameters sample splitting prediction risk asymptotic minimization

2023-07-15abs ↗pdf ↗

Approximate blocked Gibbs sampling for Bayesian neural networksstat.ML

Improved sampling for Bayesian neural networks reduces vanishing acceptance rates and increases predictive accuracy.

problem Sampling inefficiency in Bayesian neural networks, especially with deep architectures and large datasets.

method Approximate blocked Gibbs sampling to partition and sample subgroups of parameters.

result Increased predictive accuracy and quantification of predictive uncertainty in classification tasks.

Bayesian neural networks Gibbs sampling minibatch MCMC predictive accuracy vanishing acceptance rates

2022-08-24abs ↗pdf ↗

Depth Separation in Norm-Bounded Infinite-Width Neural Networkscs.LG

New findings on depth vs. width in neural networks, showing depth can improve learnability.

problem Understanding the role of depth in neural networks, especially when width is unbounded.

method Analyzing sample complexity for learnability in norm-controlled depth-2 and depth-3 ReLU networks.

result Depth can improve learnability of functions that are otherwise unlearnable with depth-2 networks.

neural networks depth separation sample complexity ReLU networks infinite width

2024-02-13abs ↗pdf ↗

Potential adversarial samples for white-box attackscs.LG

The paper identifies potential adversarial samples near decision boundaries of neural networks.

problem Vulnerability of deep neural networks to small perturbations of inputs.

method Developed a method to explore near decision boundaries of trained classifiers to identify potential adversarial samples.

result Potential adversarial samples represent only 61% of the test data but cover more than 82% of adversarial samples produced by iFGSM and 92% of those by DeepFool on CIFAR10.

adversarial samples deep neural networks decision boundaries robustness CIFAR10

2019-12-13abs ↗pdf ↗

Mutual Teaching for Graph Convolutional Networkscs.LG

Mutual teaching improves graph models with less labeled data.

problem Training graph models with limited labeled data.

method Dual model training with mutual teaching strategy.

result Significant performance improvement with less labeled data.

graph convolutional networks label propagation pseudo labeling model updating transductive learning

2020-09-02abs ↗pdf ↗

Bayesian Attention Networks for Data Compressioncs.LG

Bayesian Attention Networks compress data by focusing on key training samples.

problem Lossless data compression for efficiency.

method Bayesian Attention Networks with attention factors and latent space.

result Efficient prediction using a few correlated training samples.

Bayesian Networks Attention Mechanism Data Compression Latent Space Jensen's Inequality

2021-03-29abs ↗pdf ↗

Wide Bayesian neural networks have a simple weight posterior: theory and accelerated samplingstat.ML

Wide Bayesian neural networks have a simpler weight posterior, leading to faster MCMC sampling.

problem Sampling from the posterior of wide Bayesian neural networks is challenging.

method Introducing repriorisation, a data-dependent reparameterisation that simplifies the posterior distribution.

result The repriorisation map accelerates MCMC sampling, achieving up to 50x higher effective sample size.

Bayesian neural networks repriorisation MCMC sampling wide networks KL divergence

2022-06-15abs ↗pdf ↗

On the Study of Sample Complexity for Polynomial Neural Networkscs.LG

Paper analyzes sample complexity of polynomial neural networks.

problem Understanding the sample complexity of polynomial neural networks.

method Extends previous literature to polynomial neural networks and analyzes sample complexity.

result Obtains novel results on sample complexity of polynomial neural networks.

polynomial neural networks sample complexity generalization ability neural tangent kernel

2022-07-18abs ↗pdf ↗

DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networksmath.OC

DIGing-SGLD improves SGLD for scalable Bayesian learning in dynamic networks.

problem Scalable Bayesian learning in multi-agent systems with time-varying networks.

method Integrates Langevin sampling with gradient-tracking for decentralized learning over time-varying networks.

result Achieves geometric convergence to the target distribution with finite-time guarantees.

Bayesian learning Decentralized learning SGLD Time-varying networks Langevin sampling

2025-11-16abs ↗pdf ↗

Geometric Sampling of Networksmath.DG

Geometric sampling of networks using curvature measures.

problem Sampling and analyzing complex network structures.

method Three types of discrete curvature (Forman-, full Forman-, Haantjes-Ricci) for edge-based and node-based sampling.

result Effective detection of networks' backbone and coarse structure.

networks curvature sampling discretization Ricci flow

2020-10-28abs ↗pdf ↗

Adversarially Learned Inferencestat.ML

We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space while the inference network maps training examples in data space to the sp…

2016-06-02abs ↗pdf ↗

Higher-order accurate two-sample network inference and network hashingstat.ME

Develops a fast, accurate method for comparing networks.

problem Comparing networks with repeated observations and varying sizes/sparsity.

method A novel two-sample hypothesis testing method with theoretical guarantees.

result Outperforms existing tools in speed and accuracy, power-optimal.

network comparison two-sample hypothesis network hashing false discovery rate finite-sample accuracy

2022-08-16abs ↗pdf ↗

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networkscs.LG

New sample complexity bounds for linear predictors and neural networks, focusing on initialization.

problem Understanding sample complexity for vector-valued linear predictors and neural networks, especially under initialization-dependent conditions.

method Size-independent bounds on Frobenius norm distance from a fixed reference matrix, applying to vector-valued predictors and neural networks.

result Established new sample complexity bounds for feed-forward neural networks, resolving open questions and introducing a new learnable problem.

sample complexity linear predictors neural networks Frobenius norm initialization

2023-05-25abs ↗pdf ↗

Approximating Langevin Monte Carlo with ResNet-like Neural Network architecturescs.LG

The paper proposes a neural network architecture inspired by Langevin Monte Carlo for sampling from target distributions.

problem Sampling from complex target distributions efficiently.

method A neural network architecture inspired by Langevin Monte Carlo is proposed to map samples from a simple reference distribution to samples from the target.

result The proposed neural network architecture achieves approximation rates in the Wasserstein-2 distance for smooth, log-concave target distributions.

Langevin Monte Carlo Neural Networks Sampling Wasserstein Distance Sub-Gaussianity

2023-11-06abs ↗pdf ↗

Bayesian structure learning and sampling of Bayesian networks with the R package BiDAGstat.CO

BiDAG R package learns and samples Bayesian network structures efficiently.

problem Efficiently learning and sampling Bayesian network structures.

method Hybrid approach combining PC algorithm, iterative order MCMC, and partition MCMC.

result BiDAG can handle both discrete and continuous data.

Bayesian networks Markov chain Monte Carlo structure learning sampling R package

2021-05-02abs ↗pdf ↗

On Size-Independent Sample Complexity of ReLU Networkscs.LG

Improved sample complexity for ReLU networks with norm constraints.

problem Estimating sample complexity for ReLU networks under norm constraints.

method Refined Rademacher complexity analysis for function class.

result Often no explicit depth-dependence in sample complexity bound.

ReLU networks sample complexity Rademacher complexity norm constraints generalization

2023-06-03abs ↗pdf ↗

Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Predictioncs.LG

New method improves graph neural networks by considering different types of relations in sampling.

problem Current graph neural networks ignore relation types in biomedical graphs, leading to suboptimal performance.

method Proposes relation-dependent sampling for multi-relational graphs to balance relation frequency and importance.

result State-of-the-art graph neural networks achieve better accuracy and efficiency with relation-dependent sampling.

graph neural networks multi-relational graphs drug-drug interactions sampling relation types

2021-05-28abs ↗pdf ↗

Improving Sample Efficiency with Normalized RBF Kernelscs.LG

Improved sample efficiency with normalized RBF kernels in neural networks.

problem Learning more with less data in deep learning models.

method Two-phase method to train neural networks with normalized RBF kernels as output layer.

result Normalized RBF kernel networks achieve higher sample efficiency, compactness, and separability.

deep learning sample efficiency RBF kernels neural networks classification tasks

2020-07-30abs ↗pdf ↗

A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetrystat.ML

Paper presents a method to summarize HMC samples for neural networks, providing meaningful uncertainty estimates.

problem Lack of interpretable summary statistics for HMC samples in neural networks due to permutation symmetry.

method Introducing a transpositions metric to quantify permutations and using rebasin method to summarize HMC samples.

result Compact representation of HMC samples provides meaningful uncertainty estimates for each weight in a neural network.

Bayesian neural networks Hamiltonian Monte Carlo permutation symmetry uncertainty estimation neural network pruning

2023-12-31abs ↗pdf ↗

A State-Space Approach for Optimal Traffic Monitoring via Network Flow Samplingeess.SY

The robustness and integrity of IP networks require efficient tools for traffic monitoring and analysis, which scale well with traffic volume and network size. We address the problem of optimal large-scale flow monitoring of computer networks under resource constraints. We propose a stochastic optimization framework wh…

2013-06-24abs ↗pdf ↗

Edgeworth expansions for network momentsmath.ST

Paper provides Edgeworth expansions for network moments, improving accuracy of sampling distributions.

problem Accurate descriptions of sampling distributions of network moment statistics.

method Edgeworth expansion applied to studentized network moment statistics.

result Higher-order accurate approximation to sampling CDF of network moment statistics.

Edgeworth expansions network moments sampling distributions network inference sparsity

2020-04-14abs ↗pdf ↗

Learning the mapping

\mathbf{x}\mapsto \sum_{i=1}^d x_i^2

: the cost of finding the needle in a haystackcs.LG

Learning to approximate a separable function is hard, requiring many samples even with sparse networks.

problem Learning the separable function

x \mapsto \sum_{i=1}^d x_i^2

with limited samples.

method Sparse neural networks vs. dense neural networks, explicit regularization.

result The sample complexity for dense networks is

\mathcal{O}(d^{2.5})

with explicit regularization, better than

\mathcal{O}(d^{4})

machine learning sparse networks dense networks separable functions sample complexity

2020-02-24abs ↗pdf ↗

Optimizing Objective Functions from Trained ReLU Neural Networks via Samplingmath.OC

New algorithms optimize neural networks with ReLU activations using sampling.

problem Optimizing trained neural networks with ReLU activations.

method Iterative algorithm and enhanced algorithm using sampling and neighborhood search.

result The methods reduce the initial MIP problem into smaller LP or MIP problems.

neural networks ReLU activations optimization sampling piecewise linear

2022-05-27abs ↗pdf ↗

A Neural Network MCMC sampler that maximizes Proposal Entropystat.ML

Neural network MCMC sampler maximizes proposal entropy for efficient sampling.

problem Inefficient sampling from complex probability distributions.

method Proposes a neural network MCMC sampler that maximizes proposal entropy.

result Significantly higher efficiency in various sampling tasks.

MCMC Neural Networks Proposal Entropy Efficiency Sampling

2020-10-07abs ↗pdf ↗

Training generative neural networks via Maximum Mean Discrepancy optimizationstat.ML

We consider training a deep neural network to generate samples from an unknown distribution given i.i.d. data. We frame learning as an optimization minimizing a two-sample test statistic---informally speaking, a good generator network produces samples that cause a two-sample test to fail to reject the null hypothesis. …

2015-05-14abs ↗pdf ↗

Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samplesmath.ST

Proposes a neural network method to combine nonprobability and probability survey samples.

problem Combining nonprobability and probability survey samples for accurate population mean estimation.

method Uses a deep neural network to estimate sampling scores from nonprobability samples and combines them with probability sample information.

result Proposed estimators improve robustness to parametric propensity-score misspecification, especially for nonlinear selection mechanisms.

survey sampling doubly robust neural networks nonprobability samples probability samples

2026-05-27abs ↗pdf ↗

Sampling random graph homomorphisms and applications to network data analysismath.PR

A graph homomorphism is a map between two graphs that preserves adjacency relations. We consider the problem of sampling a random graph homomorphism from a graph into a large network. We propose two complementary MCMC algorithms for sampling random graph homomorphisms and establish bounds on their mixing times and the …

2019-10-21abs ↗pdf ↗

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequencesstat.ML

Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.

problem Understanding the impact of noise on the sample complexity of recurrent neural networks.

method Analyzing noisy multi-layered sigmoid recurrent neural networks with independent noise and proving lower bounds.

result Exponential gap in sample complexity between noisy and non-noisy networks, even for small noise values.

Recurrent Neural Networks Sample Complexity Noise PAC Learning Lower Bounds

2023-05-28abs ↗pdf ↗

Neural Networks Regularization Through Class-wise Invariant Representation Learningcs.LG

Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification task when few training samples are available. We attempt to solve this issue by pr…

2017-09-06abs ↗pdf ↗

Classification Logit Two-sample Testing by Neural Networksstat.ML

The recent success of generative adversarial networks and variational learning suggests training a classifier network may work well in addressing the classical two-sample problem. Network-based tests have the computational advantage that the algorithm scales to large samples. This paper proposes a two-sample statistic …

2019-09-25abs ↗pdf ↗