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 “distribution error”

Distributional Computational Graphs: Error Boundsstat.ML

Study error bounds in evaluating distributional computational graphs.

problem Error analysis in evaluating graphs with inputs as probability distributions.

method Establish non-asymptotic error bounds using Wasserstein-1 distance.

result Non-asymptotic error bounds for discretization errors in distributional computational graphs.

distributional computational graphs discretization error Wasserstein-1 distance error bounds

2026-01-22abs ↗pdf ↗

Learning Distributions by Generative Adversarial Networks: Approximation and Generalizationcs.LG

GANs learn distributions well from samples, with rates depending on intrinsic dimension.

problem Learning distributions from samples using GANs.

method Oracle inequality, Hölder functions approximation, neural network approximation, integral probability metrics.

result Convergence rates of GANs depend on intrinsic dimension, not ambient dimension.

GANs distribution learning finite samples approximation error generalization error

2022-05-25abs ↗pdf ↗

Generalization Error for Linear Regression under Distributed Learningstat.ML

Analyzes generalization error in distributed linear regression.

problem Understanding generalization performance in distributed learning.

method Analytical characterization of generalization error in linear regression with distributed learning.

result Generalization error increases dramatically when nodes estimate close to the number of observations.

distributed learning linear regression generalization error overparameterization network partitioning

2020-04-30abs ↗pdf ↗

Selecting a number of voters for a voting ensemblecs.LG

Optimal number of voters for a voting ensemble can be estimated from the distribution of classifier errors.

problem Finding the optimal number of voters for a voting ensemble to minimize error rate.

method Estimate the distribution of classifier errors and infer error rates for different numbers of voters.

result Lower-variance estimates of error rates can be obtained by inferring them for different numbers of voters.

voting ensemble classifier error optimal number of voters error rate estimation

2021-04-23abs ↗pdf ↗

Linear Regression with Distributed Learning: A Generalization Error Perspectivestat.ML

Study on distributed linear regression performance, focusing on generalization error.

problem Performance of distributed learning in large-scale linear regression.

method Statistical learning approach, focusing on generalization error.

result Generalization error of distributed solution can be higher than centralized solution.

distributed learning linear regression generalization error statistical learning networked computation

2021-01-22abs ↗pdf ↗

Accuracy estimation of neural networks by extreme value theorystat.ML

New method uses extreme value theory to estimate neural network errors.

problem Quantifying the error of neural networks, especially for large values.

method Applying extreme value theory to approximate the distribution of error.

result Developed a new estimator for the shape parameter of the Pareto distribution.

neural networks error estimation extreme value theory Pareto distribution

2025-11-01abs ↗pdf ↗

Epistemic Errors of Imperfect Multitask Learners When Distributions Shiftcs.LG

New framework identifies and reduces errors in machine learning under distribution shift.

problem Errors in machine learning models when distributions change.

method Developed a principled framework to characterize and eliminate epistemic errors in imperfect multitask learning.

result Provided a decompositional epistemic error bound for general settings of distribution shift.

Machine Learning Bayesian Networks Uncertainty Epistemic Error Distribution Shift

2025-05-29abs ↗pdf ↗

On Distributed Learning with Constant Communication Bitscs.IT

Paper studies distributed learning with limited communication bits, achieving optimal error exponents.

problem Distributed hypothesis testing with constant communication bits.

method Geometric approach in distribution spaces, encoding empirical distributions to transmission bits.

result Optimal achievable error exponents and coding schemes for various communication constraints.

distributed learning hypothesis testing communication constraints error exponents empirical distributions

2021-09-14abs ↗pdf ↗

Distributional Robustness Bounds Generalization Errorscs.LG

The paper connects three machine learning methods to reduce generalization errors.

problem Reducing generalization errors in machine learning models.

method Distributionally robust optimization, Bayesian methods, and regularization.

result Machine learning models can be characterized using distributional uncertainty and robustness measures.

machine learning generalization error distributional robustness Bayesian methods regularization

2022-12-20abs ↗pdf ↗

Distributional Generalization: A New Kind of Generalizationcs.LG

New generalization concept considers distribution of errors, not just average error.

problem Classical generalization fails to capture distributional differences in classifier outputs.

method Formal conjectures about distributional generalization based on model architecture, training procedure, and data distribution.

result Distributional generalization can be expected in specific conditions, as evidenced by empirical results.

generalization distributional classifier errors CIFAR-10

2020-09-17abs ↗pdf ↗

Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regimestat.ML

Sharp analysis of out-of-distribution error in overparameterized models with importance weights.

problem Understanding and quantifying the degradation of performance in overparameterized models when faced with underrepresented data.

method Sharp analysis of an overparameterized Gaussian mixture model with spurious features and cost-sensitive interpolating solutions incorporating importance weights.

result Characterization of a novel tradeoff between worst-case robustness and average accuracy as a function of importance weight magnitude.

overparameterized models out-of-distribution error importance weights sharp analysis Gaussian mixture model

2024-05-10abs ↗pdf ↗

Empirical Study of the GARCH model with Rational Errorsq-fin.CP

We use the GARCH model with a fat-tailed error distribution described by a rational function and apply it for the stock price data on the Tokyo Stock Exchange. To determine the model parameters we perform the Bayesian inference to the model. The Bayesian inference is implemented by the Metropolis-Hastings algorithm wit…

2013-12-26abs ↗pdf ↗

Fast and Multiphase Rates for Nearest Neighbor Classifiersstat.ML

This research examines how the error rate of nearest neighbor classifiers varies with dataset size.

problem The scaling of classification error rates with dataset size is not uniform.

method Theoretical analysis of nearest neighbor classifiers, focusing on early and late phases of dataset size.

result The error rate of nearest neighbor classifiers can have fine-grained rates depending on the dataset size and data distribution.

nearest neighbor classifiers classification error rates dataset size early phase late phase

2023-08-16abs ↗pdf ↗

Step-Ahead Error Feedback for Distributed Training with Compressed Gradientcs.LG

New techniques improve distributed training with compressed gradients.

problem Gradient mismatch problem in local error feedback.

method Step-ahead error feedback and error averaging techniques.

result Our methods handle gradient mismatch and train faster than full-precision training.

distributed training gradient compression local error feedback gradient mismatch step-ahead

2020-08-13abs ↗pdf ↗

Non-Convex SGD Learns Halfspaces with Adversarial Label Noisecs.LG

Non-convex SGD learns halfspaces with adversarial label noise efficiently.

problem Agnostically learning halfspaces in adversarial label noise settings.

method Non-convex SGD optimization for halfspace learning.

result Non-convex SGD achieves misclassification error close to optimal with adversarial noise.

SGD halfspaces PAC model log-concave distributions adversarial noise

2020-06-11abs ↗pdf ↗

An error analysis of generative adversarial networks for learning distributionscs.LG

This study analyzes how well GANs approximate distributions from small samples.

problem Understanding how well GANs approximate distributions from limited data.

method Analysis of GANs using integral probability metrics and Hölder classes.

result GANs can adaptively learn low-dimensional structures or Hölder densities.

GANs probability distributions integral probability metrics Hölder classes Wasserstein distance

2021-05-27abs ↗pdf ↗

A Concentration Bound for Distributed Stochastic Approximationstat.ML

High-probability bound for distributed stochastic approximation tracking error.

problem Analyzing the convergence of distributed stochastic approximation schemes.

method Analysis using ODE approach to stochastic approximation.

result High probability bound for tracking error between iterates and limiting differential equation.

distributed stochastic approximation consensus tracking error ODE approach stochastic approximation

2022-10-09abs ↗pdf ↗

Multiple imputation using chained random forests: a preliminary study based on the empirical distribution of out-of-bag prediction errorsstat.ME

A new method uses RF's out-of-bag errors for multiple imputation.

problem Missing data in biomedical studies and lack of prediction uncertainty.

method Constructs conditional distributions from the empirical distribution of out-of-bag prediction errors.

result Valid multiple imputation results achieved without parametric assumptions.

multiple imputation random forests out-of-bag errors prediction uncertainty empirical distribution

2020-04-30abs ↗pdf ↗

Convergence of Continuous Normalizing Flows for Learning Probability Distributionsstat.ML

CNFs learn distributions from samples with error bounds.

problem Learning probability distributions from finite samples.

method Continuous normalizing flows with linear interpolation and flow matching objective function.

result Non-asymptotic error bounds for distribution estimator in Wasserstein-2 distance.

continuous normalizing flows probability distributions finite samples Wasserstein-2 distance log-concave distributions

2024-03-31abs ↗pdf ↗

Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Frameworkstat.ML

Unified framework for error quantification in off-policy evaluation with distributional shift.

problem Establishing high-confidence CI for target policy value from offline data.

method Unified error analysis quantifying misspecification and sampling errors.

result Achieves tightest possible CI and robustness against distributional shifts.

off-policy evaluation confidence interval distributional shift Markov decision processes error quantification

2023-09-23abs ↗pdf ↗

Heterogeneity Matters even More in Distributed Learning: Study from Generalization Perspectivecs.LG

Study shows data heterogeneity affects distributed learning's generalization error.

problem Effect of data heterogeneity on distributed learning performance.

method Established bounds on generalization error using information-theoretic rate-distortion theory.

result Data heterogeneity improves generalization error for distributed learning.

data heterogeneity distributed learning generalization error information theory Support Vector Machines

2025-03-03abs ↗pdf ↗

Quantized Adam with Error Feedbackcs.LG

Quantized Adam reduces communication cost in deep learning training.

problem Reducing communication cost in distributed deep learning training.

method Gradient and weight quantization with error feedback in Adam.

result Proposed methods converge to first-order stationary points.

Quantized Adam Distributed Deep Learning Error Feedback Gradient Quantization Weight Quantization

2020-04-29abs ↗pdf ↗

An Improved Algorithm for Learning Drifting Discrete Distributionscs.LG

New algorithm learns changing discrete distributions with minimal drift error.

problem Learning discrete distributions that change over time with limited past samples.

method Adaptive algorithm using data-dependent bounds to balance statistical and drift errors.

result Tighter statistical error bounds for drifting distributions with or without finite support.

distribution drift adaptive learning discrete distributions statistical error data-dependent bounds

2024-03-08abs ↗pdf ↗

Finite Sample Guarantees for Distributed Online Parameter Estimation with Communication Costseess.SY

The paper provides bounds on estimation error in a distributed online learning setting.

problem Estimating an unknown parameter in a distributed and online manner with finite sample guarantees.

method Proposes a distributed online estimation algorithm that improves accuracy through communication, providing non-asymptotic bounds on estimation error.

result Demonstrates a trade-off between estimation error and communication costs, and determines a stopping time for communication based on desired accuracy.

distributed learning online estimation finite sample guarantees estimation error communication costs

2022-09-12abs ↗pdf ↗

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regretcs.LG

Learning reward functions can lead to poor policy performance despite low error.

problem Low error in learned reward functions does not guarantee low regret in policy performance.

method Mathematical analysis of reward learning and policy optimization.

result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.

reinforcement learning reward learning regret policy optimization distributional shift

2024-06-22abs ↗pdf ↗

CSER: Communication-efficient SGD with Error Resetcs.LG

CSER improves SGD efficiency by resetting errors and partial synchronization.

problem Limited scalability of Distributed Stochastic Gradient Descent (SGD) due to communication bottlenecks.

method Introduces 'error reset' technique and partial synchronization for gradients and models.

result Proves convergence for smooth non-convex problems and accelerates distributed training significantly.

SGD communication efficiency error reset partial synchronization distributed training

2020-07-26abs ↗pdf ↗

Some observations concerning Off Training Set (OTS) errorcs.LG

A form of generalisation error known as Off Training Set (OTS) error was recently introduced in [Wolpert, 1996b], along with a theorem showing that small training set error does not guarantee small OTS error, unless assumptions are made about the target function. Here it is shown that the applicability of this theorem …

2019-11-18abs ↗pdf ↗

Learning Algorithm Generalization Error Bounds via Auxiliary Distributionscs.LG

New method improves understanding of machine learning model performance.

problem Understanding how well machine learning models generalize from training data to unseen data.

method Auxiliary Distribution Method to derive new generalization error bounds.

result Upper bounds on generalization errors are tighter and more applicable.

machine learning generalization error supervised learning auxiliary distribution Jensen-Shannon divergence

2022-10-02abs ↗pdf ↗

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learningcs.LG

Enhances reinforcement learning uncertainty estimation with a generalized Gaussian error model.

problem Inaccurate error representations and compromised uncertainty estimation in conventional uncertainty-aware TD learning.

method Introduces a novel framework for generalized Gaussian error modeling in deep reinforcement learning, incorporating higher-order moments, particularly kurtosis, to improve uncertainty estimation and mitigation.

result Significant performance gains in policy gradient algorithms with the proposed framework.

Reinforcement Learning Temporal Difference Learning Uncertainty Estimation Generalized Gaussian Distribution Aleatoric Uncertainty

2024-08-05abs ↗pdf ↗

Non-Asymptotic Error Bounds for Bidirectional GANscs.LG

Sharp error bounds derived for bidirectional GANs without restrictive assumptions.

problem Estimating the error of bidirectional GANs under various conditions.

method Dudley distance, neural network functions, decomposition of IPM.

result Nearly sharp bounds for bidirectional GAN estimation error.

bidirectional GAN Dudley distance neural networks integral probability metric empirical distributions

2021-10-24abs ↗pdf ↗

Consistent DAG selection for Bayesian causal discovery under general error distributionsmath.ST

Bayesian method identifies causal DAG structure from non-Gaussian errors.

problem Learning causal structure from non-Gaussian errors in Bayesian networks.

method Bayesian hierarchical model with DAG prior for non-Gaussian errors.

result Posterior DAG selection consistency achieved under mild assumptions.

Bayesian causal discovery non-Gaussian errors DAG selection scale mixture of Gaussian

2025-08-01abs ↗pdf ↗

\mathscr{H}

-Consistency Estimation Error of Surrogate Loss Minimizerscs.LG

Study of estimation errors in surrogate loss minimizers, providing stronger guarantees than existing methods.

problem Estimation errors in surrogate loss minimizers for various hypothesis sets.

method Detailed study of

\mathscr{H}

-consistency estimation error bounds, proving general theorems for distribution-dependent and independent settings.

result Explicit bounds for zero-one and adversarial losses, showing enhancements under distributional assumptions.

estimation errors surrogate loss minimizers hypothesis set distribution-dependent distribution-independent

2022-05-16abs ↗pdf ↗

Robust Mean Estimation Without Moments for Symmetric Distributionscs.DS

Efficiently estimates mean of symmetric distributions without moments.

problem Estimating mean of symmetric distributions without moment assumptions.

method Generalization of filtering technique, Huber-loss-based techniques, SoS proofs.

result Achieves optimal error bounds for various symmetric distributions.

mean estimation symmetric distributions moment assumptions filtering technique Huber-loss

2023-02-21abs ↗pdf ↗

Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learningstat.ML

New bounds on generalization error for distributed learning using rate-distortion theory.

problem Establishing upper bounds on generalization error for distributed learning algorithms.

method Using rate-distortion theory, the paper introduces new bounds that depend on the compressibility of each client's algorithm.

result The bounds suggest that the generalization error of the distributed setting decays faster than that of the centralized one with a factor of

\mathcal{O}(\log(K)/\sqrt{K})

rate-distortion theory distributed learning generalization error statistical learning federated learning

2022-06-06abs ↗pdf ↗

On the Robustness of Langevin Dynamics to Score Function Errorcs.LG

Langevin dynamics fails to produce accurate samples even with small score function errors.

problem Robustness of Langevin dynamics to score function errors.

method Analysis of Langevin dynamics and score function errors.

result Langevin dynamics produces a distribution far from the target distribution in TV distance even with small

L^2

errors in the score function.

Langevin dynamics score function robustness diffusion models Total Variation (TV) distance

2026-03-11abs ↗pdf ↗

Not All Learnable Distribution Classes are Privately Learnablecs.DS

Example shows learnable distributions not privately learnable.

problem Learnable distributions under non-private conditions not transferable to differential privacy.

method Example of a distribution class learnable up to constant error in total variation distance but not under differential privacy.

result Contradicts conjecture of Ashtiani on learnability under differential privacy.

differential privacy distribution learning total variation distance

2024-02-01abs ↗pdf ↗

Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimizationstat.ML

The paper tackles gradual domain adaptation with manifold-constrained DRO, showing error bounds across distributions.

problem Gradual domain adaptation challenge with manifold-constrained data distributions.

method Distributionally Robust Optimization (DRO) with an adaptive Wasserstein radius.

result Theoretical bounds on classification error across distributions, demonstrating error propagation dynamics.

domain adaptation manifold-constrained distributionally robust optimization Wasserstein distance compatibility measure

2024-10-17abs ↗pdf ↗

Error Analysis of Discrete Flow with Generator Matchingmath.ST

Unified error analysis for discrete flow models.

problem Error analysis of discrete flow models.

method Stochastic calculus theory, Girsanov theorem, generator matching, uniformization.

result First error analysis for discrete flow models.

discrete flow error analysis stochastic calculus Girsanov theorem generator matching

2025-09-26abs ↗pdf ↗

Subsampling Error in Stochastic Gradient Langevin Diffusionsstat.ML

SGLDiff approximates Bayesian posterior distributions with subsampling error.

problem Approximating Bayesian posterior distributions in large-scale data settings.

method Stochastic Gradient Langevin Diffusion (SGLDiff) with subsampling.

result The Wasserstein distance between the posterior and SGLDiff's limiting distribution is bounded by a fractional power of the mean waiting time.

Bayesian posterior Stochastic Gradient Langevin Diffusion Subsampling Ergodicity Wasserstein distance

2023-05-23abs ↗pdf ↗

Robust Variable Selection for High-dimensional Regression with Missing Data and Measurement Errorsstat.ME

Robust variable selection for high-dimensional data with missing and measurement errors.

problem Missing data and measurement errors confound data distribution.

method Exponential loss function with inverse probability weighting and additive error models.

result The Atan punishment method improves robust variable selection.

variable selection missing data measurement errors robustness exponential loss

2024-10-22abs ↗pdf ↗

Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspectivecs.AI

This paper analyzes errors in Shapley value-based model explanations.

problem Biased or unreliable explanations from existing SVA methods.

method Error theoretical analysis framework decomposing errors into observation and structural biases.

result Trade-off between observation and structural biases in SVA explanations.

Shapley value explainable AI model explanations error analysis bias

2024-04-21abs ↗pdf ↗

Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shiftstat.ML

Paper introduces a novel measure to analyze excess error in classification under covariate shift.

problem Analyzing excess error in classification under covariate shift.

method Utilizes vicinity information to characterize excess error.

result Faster or competitive convergence rates compared to previous techniques.

transfer learning covariate shift excess error vicinity information

2024-05-27abs ↗pdf ↗

An Explicit Sampling Dependent Spectral Error Bound for Column Subset Selectionmath.NA

In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the …

2015-05-04abs ↗pdf ↗

Classification Error Bound for Low Bayes Error Conditions in Machine Learningcs.LG

This work bounds classification error in machine learning for low Bayes error conditions.

problem Understanding the error mismatch between Bayes error and model-based classification error.

method Applying classification error bounds to study the relationship with Kullback-Leibler divergence and proposing a linear approximation for low Bayes error conditions.

result A linear approximation of the classification error bound for low Bayes error conditions is proposed.

classification error Bayes decision rule Kullback-Leibler divergence machine learning low Bayes error

2025-01-27abs ↗pdf ↗

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errorsstat.ML

Score matching errors are not sufficient for measuring diffusion model quality.

problem The

L^2

score matching error is not a reliable measure of diffusion model performance.

method Decomposed score errors into gradient and solenoidal components and analyzed their geometric properties.

result Only the gradient component of the score error affects the marginal distributional quality.

score matching diffusion models geometric analysis Fokker-Planck dynamics Kullback-Leibler divergence

2026-06-04abs ↗pdf ↗

Moments and Root-Mean-Square Error of the Bayesian MMSE Estimator of Classification Error in the Gaussian Modelstat.ML

The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifier design because the error must be estimated using the same data from which the classifier has been…

2013-10-05abs ↗pdf ↗

In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustnesscs.LG

In-N-Out improves model robustness to out-of-distribution data.

problem Learning robust models with few in-distribution labeled examples.

method Pre-training with auxiliary information and self-training with pseudolabels.

result In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.

robustness pre-training self-training auxiliary information out-of-distribution

2020-12-08abs ↗pdf ↗

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errorsstat.ML

New geometric analysis shows $L^2$ score error is flawed for diffusion models.

problem Score matching errors in diffusion models do not fully capture distributional quality.

method Decomposed score errors into gradient and solenoidal components, focusing on gradient's role in Fokker-Planck dynamics.

result Only gradient component affects marginal distributional quality; solenoidal component is structurally invisible.

diffusion models score matching geometric analysis Fokker-Planck Kullback-Leibler divergence

2026-06-04abs ↗pdf ↗