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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “high regularity”

Biharmonic wave maps: Local wellposedness in high regularitymath.AP

High regularity biharmonic wave maps shown to be locally well-posed.

problem Local wellposedness of biharmonic wave maps with high Sobolev regularity.

method Vanishing viscosity and parabolic regularization to prove existence; geometric nature exploited.

result Local wellposedness established in high Sobolev regularity.

biharmonic wave maps local wellposedness high regularity vanishing viscosity parabolic regularization

2019-03-05abs ↗pdf ↗

High-Dimensional Linear Regression via Implicit Regularizationmath.ST

New method implicitly regularizes high-dimensional linear regression using gradient descent.

problem Sparse vector estimation in high-dimensional linear regression.

method Gradient descent on residual sum of squares with early stopping under overparameterization.

result Gradient descent implicitly leads to nearly sparse optimal solutions without explicit penalties.

high-dimensional linear regression implicit regularization gradient descent sparse estimation overparameterization

2019-03-22abs ↗pdf ↗

The role of regularization in classification of high-dimensional noisy Gaussian mixturestat.ML

Regularization helps improve classification of noisy high-dimensional data.

problem Classifying high-dimensional noisy Gaussian mixture with limited oracle knowledge.

method Analysis of regularized convex classifiers including ridge, hinge, and logistic regression.

result Regularization can reach Bayes-optimal performance under certain conditions.

regularization classification Gaussian mixture high-dimensional noisy data

2020-02-26abs ↗pdf ↗

Expert-guided Regularization via Distance Metric Learningcs.LG

DMLreg uses expert knowledge to improve model performance in high-dimensional settings.

problem Improving model performance in high-dimensional prediction problems.

method Learning a Mahalanobis distance metric from expert comparisons and integrating it into a regularized linear model.

result DMLreg leads to improvements in model performance when expert knowledge is relevant.

Distance Metric Learning Regularization High-dimensional Prediction Expert Knowledge Linear Model

2019-12-09abs ↗pdf ↗

Temporal Regularization in Markov Decision Processcs.LG

Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus o…

2018-11-01abs ↗pdf ↗

Consistent Semi-Supervised Graph Regularization for High Dimensional Datacs.LG

A new method improves graph-based learning for high-dimensional data.

problem Inconsistent high-dimensional learning efficiency of semi-supervised graph regularization.

method Introducing a novel regularization approach involving centering operation.

result Empirical results show improved performance over spectral clustering.

graph regularization semi-supervised learning high dimensional data centering operation spectral clustering

2020-06-13abs ↗pdf ↗

Regularized Estimation and Feature Selection in Mixtures of Gaussian-Gated Experts Modelsstat.ML

Regularized MLE improves MoE models for high-dimensional data.

problem Modeling with high-dimensional predictors and feature selection.

method Gaussian gating network,

\ell_1

-regularized MLE, EM-Lasso algorithm, BIC-like criterion.

result Regularized MLE outperforms standard MLE in clustering and regression tasks.

Gaussian gating network regularized MLE EM-Lasso BIC high-dimensional predictors

2019-09-12abs ↗pdf ↗

Asymptotics of high-codimensional area-minimizing currents in hyperbolic spacemath.DG

Study on high-codimensional minimal surfaces in hyperbolic space.

problem Understanding high-codimensional minimal surfaces in hyperbolic space.

method Investigating asymptotic behavior and boundary regularity of area-minimizing currents.

result Established boundary regularity results for high-codimensional minimal surfaces near their asymptotic boundaries.

minimal surfaces hyperbolic space asymptotic behavior boundary regularity codimensional currents

2026-01-07abs ↗pdf ↗

Learning Pareto manifolds in high dimensions: How can regularization help?stat.ML

The paper explores how regularization can improve multi-objective learning with high-dimensional data.

problem Improving multi-objective learning with high-dimensional and costly data.

method A two-stage MOL framework that leverages low-dimensional structure.

result Vanilla regularization approaches often fail in multi-objective learning, and a two-stage framework can successfully exploit low-dimensional structure.

multi-objective learning high-dimensional data vanilla regularization low-dimensional structure fairness-risk trade-offs

2025-03-11abs ↗pdf ↗

On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Boundsstat.ML

This work analyzes how to choose regularization norms for adversarial training in high dimensions.

problem Choosing the right regularization norm for adversarial training in high-dimensional settings.

method Derives asymptotic descriptions and uniform convergence bounds for robust, regularized empirical risk minimizers.

result Characterizes the relationship between perturbation size and optimal regularization choice.

Adversarial Training Regularization High-Dimensional Asymptotics Uniform Convergence Robust Empirical Risk Minimizer

2024-10-21abs ↗pdf ↗

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularizationstat.ML

The paper analyzes how re-weighting helps in reducing variance in high-dimensional kernel methods under covariate shifts.

problem The challenge of high-dimensional kernel methods under covariate shifts and the role of re-weighting.

method Derives asymptotic expansion of high-dimensional kernels under covariate shifts, analyzes bias-variance decomposition, and characterizes the regularized kernel.

result Re-weighting helps in decreasing variance and can be seen as a data-dependent regularization.

kernel ridge regression covariate shift re-weighting bias-variance decomposition high-dimensional

2024-06-05abs ↗pdf ↗

Dropout as a Regularizer of Interaction Effectscs.LG

Dropout regularizes against high-order interactions by canceling interaction rates.

problem Overfitting to high-order interactions in neural networks.

method Analyzes Dropout through the lens of interaction effects, showing how it effectively cancels out the probability of surviving interactions of different orders.

result Dropout regularizes against high-order interactions by effectively canceling out the probability of surviving interactions of different orders.

Dropout Regularization Interaction Effects Neural Networks Regularizers

2020-07-02abs ↗pdf ↗

Spatially regularized active diffusion learning for high-dimensional imagescs.LG

A new method classifies high-dimensional images with minimal labels using diffusion geometry.

problem Classifying high-dimensional images efficiently and accurately.

method Spatially-regularized nonlinear diffusion geometry for clustering and active learning.

result High-accuracy labelings achieved with a very small number of training labels.

active learning high-dimensional images diffusion geometry cluster cores spatial regularization

2019-11-06abs ↗pdf ↗

High-Dimensional Tail Index Regressionstat.ML

The study introduces a high-dimensional tail index model for viral post analysis.

problem Empirical observation of power-law distributions in viral posts.

method High-dimensional tail index regression model, regularized estimator, debiasing for inference.

result Consistency and asymptotic normality of debiased estimator.

tail index high-dimensional power-law viral posts social media

2024-03-02abs ↗pdf ↗

Measuring tail risk at high-frequency: An

L_1

-regularized extreme value regression approach with unit-root predictorsecon.EM

Study tail risk in high-frequency finance using $L_1$ -regularized regression.

problem Measuring tail risk dynamics in high-frequency financial markets.

method Dynamic extreme value regression model with

L_1

-regularized maximum likelihood estimator.

result Severity of extreme losses well predicted by low price impact in high volatility periods.

tail risk high-frequency finance extreme value regression L1 regularization unit-root predictors

2023-01-03abs ↗pdf ↗

Neural Posterior Regularization for Likelihood-Free Inferencecs.LG

This paper introduces NPR, a technique to improve Bayesian inference for multi-modal, high-dimensional simulations.

problem Challenges in Bayesian inference for multi-modal, high-dimensional simulations.

method Introduces Neural Posterior Regularization (NPR) to enforce exploration of input parameter space.

result Empirically validated that NPR significantly improves performance on various simulation tasks.

Bayesian inference Likelihood-free inference Multi-modal posterior High-dimensional simulation Regularization

2021-02-15abs ↗pdf ↗

Statistical Estimation of High-Dimensional Vector Autoregressive Modelsstat.ML

Paper proposes a new sparsity scheme for high-dimensional VAR models.

problem Estimation of high-dimensional VAR models with sparsity assumptions.

method Regularized estimation procedures for sparse VAR models.

result Threholding extends consistency properties of regularized estimators.

VAR models high-dimensional sparsity regularization time series

2020-06-09abs ↗pdf ↗

Non-convex regularization in remote sensingstat.ML

In this paper, we study the effect of different regularizers and their implications in high dimensional image classification and sparse linear unmixing. Although kernelization or sparse methods are globally accepted solutions for processing data in high dimensions, we present here a study on the impact of the form of r…

2016-06-23abs ↗pdf ↗

Spectral Dynamics and Regularization for High-Dimensional Copulasecon.EM

Novel model captures high-dimensional copulas with spectral dynamics and regularization.

problem Modeling time-varying, asymmetric, tail-dependent copulas in high dimensions.

method Score-driven dynamics for eigenvalues, non-linear shrinkage for biases, parsimonious and scalable.

result Model outperforms recent alternatives in capturing co-movements and diversification potential.

copulas spectral dynamics regularization high dimensions time-varying

2026-01-19abs ↗pdf ↗

Neural Stein critics with staged

L^2

-regularizationstat.ML

The paper introduces a novel method for training neural network Stein critics with staged $L^2$ -regularization.

problem Learning to differentiate model distributions from observed data in high-dimensional settings.

method Developed a novel staging procedure for

L^2

regularization over training time, leveraging the advantages of highly-regularized training at early times.

result Theoretical guarantees and empirical validation show that the method improves the approximation of the training dynamic by the kernel optimization, leading to faster convergence and better performance.

Stein discrepancy Neural network Regularization Kernel optimization High-dimensional data

2022-07-07abs ↗pdf ↗

Interpretation of High-Dimensional Linear Regression: Effects of Nullspace and Regularization Demonstrated on Battery Datastat.ML

The nullspace and regularization impact high-dimensional linear regression interpretability.

problem Interpreting high-dimensional linear regression coefficients in complex data.

method Optimization formulation to compare coefficients and physical knowledge.

result Regularization and z-scoring choices affect interpretability and true coefficient closeness.

high-dimensional regression nullspace interpretability battery data regularization

2023-09-01abs ↗pdf ↗

Spectral Norm Regularization for Improving the Generalizability of Deep Learningstat.ML

We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to perturbation, we propose a simple and effective regularization method, referred to as spe…

2017-05-31abs ↗pdf ↗

Empirical Hypothesis Space Reductioncs.LG

Paper proposes an algorithm to reduce hypothesis space for faster convergence in high-dimensional settings.

problem Over-conservativeness of existing regularization approaches in high-dimensional settings.

method Empirical hypothesis space reduction to achieve faster convergence without dependence on the size of the hypothesis space.

result Achieves faster convergence of generalization error

O(\sqrt{\log n/n})

independent of the dimension

d

regularization hypothesis space empirical reduction generalization error high-dimensional settings

2019-09-04abs ↗pdf ↗

Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learningcs.LG

Mutual-information regularization improves RL algorithms, especially in high-dimensional domains.

problem Value overestimation and exploration in reinforcement learning.

method Developed a novel mutual-information regularized actor-critic learning (MIRACLE) algorithm.

result MIRACLE outperforms state-of-the-art algorithms in continuous action spaces.

reinforcement learning actor-critic mutual-information Markov Decision Processes high-dimensional domains

2019-09-11abs ↗pdf ↗

High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviationsmath.ST

Interpolating models can have heavy-tailed risk, leading to rare but severe errors.

problem Interpolating models' tail risk is poorly understood, affecting rare but impactful errors.

method Large-deviation methods to study the fragility of high-dimensional linear interpolators.

result Ridgeless regression exhibits heavy-tailed risk, while ridge-regularized estimators have better tail behavior.

interpolation high-dimensional large-deviations ridgeless ridge-regularization

2026-07-10abs ↗pdf ↗

High Dimensional Classification via Regularized and Unregularized Empirical Risk Minimization: Precise Error and Optimal Lossstat.ML

The article analyzes high-dimensional classification using empirical risk minimization with precise error predictions.

problem Classifying high-dimensional data with Gaussian mixture models.

method Theoretical analysis of ridge-regularized and unregularized empirical risk minimization for high-dimensional Gaussian mixture separation.

result The square loss is optimal for high-dimensional classification in both ridge-regularized and unregularized cases.

high dimensional classification empirical risk minimization ridge regularization Gaussian mixture optimal loss

2019-05-31abs ↗pdf ↗

A multiobjective continuation method to compute the regularization path of deep neural networkscs.LG

Algorithm approximates regularization path for deep neural networks efficiently.

problem Computing the regularization path for high-dimensional deep neural networks.

method Multiobjective continuation method for non-smooth objectives.

result Approximation of the entire Pareto front for regularization path.

deep neural networks regularization path multiobjective optimization high-dimensional non-smooth

2023-08-23abs ↗pdf ↗

Dynamic Regularized CBDT: Variance-Calibrated Causal Boosting for Interpretable Heterogeneous Treatment Effectscs.LG

Dynamic CBDT improves treatment effect estimation in clinical data.

problem Estimating heterogeneous treatment effects in observational data with high accuracy and interpretability.

method Dynamic Regularized Causal Boosted Decision Trees (CBDT) integrating variance regularization and calibration.

result Significantly improved estimation accuracy and reliable coverage of true treatment effects.

heterogeneous treatment effects clinical data dynamic regularization gradient boosted decision trees calibration

2025-04-18abs ↗pdf ↗

The Impact of Regularization on High-dimensional Logistic Regressionstat.ML

Regularization improves logistic regression performance in high-dimensional settings.

problem Improving logistic regression in scenarios with many parameters and observations.

method Introducing a convex regularizer to the negative log-likelihood function to encourage desired structures.

result Explicit expressions for various performance metrics of regularized logistic regression are derived.

logistic regression high-dimensional regularization maximum likelihood performance metrics

2019-06-10abs ↗pdf ↗

Convexity of weakly regular surfaces of distributional nonnegative intrinsic curvaturemath.DG

Convex surfaces derived from specific Riemannian manifolds with high regularity.

problem Proving convexity of surfaces derived from Riemannian manifolds.

method Analyzing solutions to the very weak Monge-Ampère equation.

result Proved convexity of weakly regular surfaces with nonnegative intrinsic curvature.

Convex surfaces Riemannian manifolds Monge-Ampère equation Gaussian curvature High regularity

2022-06-18abs ↗pdf ↗

Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce datastat.ML

Generative algorithms learn high-dimensional data efficiently and generate new samples.

problem Learning from scarce high-dimensional data.

method Lipschitz-regularized gradient flows and particle-based algorithms.

result Correctly transports gene expression data points with high dimensionality.

data integration particle algorithms Lipschitz regularization Kullback-Leibler divergence high-dimensional data

2022-10-31abs ↗pdf ↗

Kernel regression in high dimensions: Refined analysis beyond double descentstat.ML

The paper analyzes high-dimensional kernel regression, showing different risk curves based on data and regularization.

problem Characterizing generalization properties of high-dimensional kernel ridge regression.

method Bias-variance decomposition of the expected excess risk, considering different regularization schemes and data eigen-profiles.

result The risk curve of kernel regression can be double-descent-like, bell-shaped, or monotonic, depending on n, d, and regularization level.

kernel regression high dimensions bias-variance generalization regularization

2020-10-06abs ↗pdf ↗

High-dimensional classification problems with Barron regular boundaries under margin conditionscs.LG

Neural networks can approximate high-dimensional classifiers with ReLU networks under margin conditions.

problem Approximating high-dimensional discontinuous classifiers with neural networks.

method Using ReLU neural networks with three hidden layers, approximating a classifier with a Barron-regular decision boundary.

result High-dimensional discontinuous classifiers can be approximated with a rate of

n^{-1}

under strong margin conditions.

Neural Networks ReLU Networks Barron Regular Margin Conditions High-Dimensional Classification

2024-12-10abs ↗pdf ↗

A Unified Framework for Estimation of High-dimensional Conditional Factor Modelsecon.EM

Unified framework for estimating high-dimensional conditional factor models.

problem Estimating high-dimensional conditional latent factor models with practical limitations.

method Constrained nuclear norm regularization and cross-validation for parameter selection.

result Imposing homogeneity improves model predictability, with new method outperforming alternatives.

factor models high-dimensional conditional nuclear norm constrained regularization

2022-09-01abs ↗pdf ↗

Stability Approach to Regularization Selection (StARS) for High Dimensional Graphical Modelsstat.ML

A challenging problem in estimating high-dimensional graphical models is to choose the regularization parameter in a data-dependent way. The standard techniques include $K$ -fold cross-validation ( $K$ -CV), Akaike information criterion (AIC), and Bayesian information criterion (BIC). Though these methods work well for lo…

2010-06-16abs ↗pdf ↗

Error Bounds for Generalized Group Sparsitystat.ML

New theorem for generalized group sparsity improves consistency and convergence rates.

problem Improving statistical inference in high-dimensional data with element-wise and group-wise sparsity.

method Developed a generalized version of Sparse-Group Lasso and proved a universal theorem for consistency and convergence rates.

result Obtained results on consistency and convergence rates for different forms of double sparsity regularization.

sparsity regularization statistical inference high-dimensional data consistency convergence rates

2020-08-08abs ↗pdf ↗

Sparse estimation via

\ell_q

optimization method in high-dimensional linear regressionstat.ML

The paper analyzes $\ell_q$ optimization methods for high-dimensional linear regression.

problem Estimating sparse parameters from noisy observations in high-dimensional settings.

method Introduces and analyzes

\ell_q

optimization methods for sparse estimation.

result Shows stable recovery properties and bounds for

\ell_q

minimization and regularization methods.

sparse estimation high-dimensional linear regression ℓ_q optimization ℓ_q minimization ℓ_q regularization

2019-11-12abs ↗pdf ↗

Is completeness necessary? Estimation in nonidentified linear modelsmath.ST

Modern data analysis depends increasingly on estimating models via flexible high-dimensional or nonparametric machine learning methods, where the identification of structural parameters is often challenging and untestable. In linear settings, this identification hinges on the completeness condition, which requires the …

2017-09-11abs ↗pdf ↗

Statistical Inverse Problems in Hilbert Scalesmath.ST

The paper analyzes Tikhonov regularization in Hilbert scales for statistical inverse problems.

problem Statistical inverse problems in Hilbert scales with general noise.

method Tikhonov regularization scheme with conditional stability estimates and high probability error bounds.

result Explicit rates of convergence for oversmoothing and regular cases over defined regularity classes.

Tikhonov regularization statistical inverse problems Hilbert scales conditional stability high probability estimates

2022-08-28abs ↗pdf ↗

Control Regularization for Reduced Variance Reinforcement Learningcs.LG

New method reduces variance in reinforcement learning.

problem High variance in reinforcement learning models.

method Functional regularization of deep policies to stabilize learning.

result Significantly reduced variance and improved stability.

reinforcement learning variance reduction functional regularization deep policy

2019-05-14abs ↗pdf ↗

Neural Network Training Using

\ell_1

-Regularization and Bi-fidelity Datastat.ML

New neural network training method uses bi-fidelity data to reduce errors.

problem Training neural networks with limited high-fidelity data.

method Bi-fidelity

\ell_1

-regularization strategies.

result Bi-fidelity

\ell_1

-regularization reduces errors by one order of magnitude.

neural networks regularization bi-fidelity sparsity uncertainty propagation

2021-05-27abs ↗pdf ↗

Manifold Regularization for Locally Stable Deep Neural Networksstat.ML

New regularization techniques improve stability of deep neural networks.

problem Improving stability of deep neural networks in high-dimensional data.

method Apply manifold regularization to develop new regularizers based on graph Laplacian sparsification.

result Empirically, networks achieve high stability in various perturbation models, including adversarial attacks.

deep learning manifold regularization graph Laplacian stability adversarial robustness

2020-03-09abs ↗pdf ↗

Variable Selection and Regularization via Arbitrary Rectangle-range Generalized Elastic Netstat.ML

ARGEN method improves variable selection and regularization in high-dimensional sparse models.

problem Constrained variable selection and regularization in high-dimensional sparse linear models.

method ARGEN penalty method, variable selection and regularization.

result ARGEN method has variable selection and estimation consistency under certain conditions.

variable selection regularization high-dimensional sparse models elastic net

2021-12-14abs ↗pdf ↗

Macroeconomic Forecasting and Machine Learningecon.EM

The paper uses machine learning to forecast macroeconomic outcomes with high-dimensional data.

problem Forecasting the full conditional distribution of macroeconomic outcomes.

method Systematically integrating three key principles: high-dimensional data with regularization, rigorous out-of-sample validation, and incorporating nonlinearities.

result Regularization via shrinkage is essential to control model complexity, while nonlinearities yield limited improvements in predictive accuracy.

macroeconomic forecasting machine learning high-dimensional data regularization out-of-sample validation

2025-10-13abs ↗pdf ↗

Efficient Regularized Regression for Variable Selection with L0 Penaltycs.LG

Variable (feature, gene, model, which we use interchangeably) selections for regression with high-dimensional BIGDATA have found many applications in bioinformatics, computational biology, image processing, and engineering. One appealing approach is the L0 regularized regression which penalizes the number of nonzero fe…

2014-07-28abs ↗pdf ↗

Auditing Differential Privacy in High Dimensions with the Kernel Quantum Rényi Divergencecs.LG

New divergences help audit DP in high dimensions.

problem Challenges in auditing DP in high-dimensional data.

method Propose kernel Rényi divergence and its regularized version for auditing.

result Regularized kernel Rényi divergence can be estimated from samples in high dimensions.

differential privacy high dimensions kernel divergence Rényi divergence auditing

2022-05-27abs ↗pdf ↗

Generalized Information Criteria for Structured Sparse Modelsstat.ME

New GIC improves model selection for structured sparse models.

problem Model selection and regularization in high-dimensional scenarios.

method Proposes a new Generalized Information Criteria (GIC) for structured sparse models.

result Obtains non-asymptotic model selection bounds and sufficient conditions for model selection consistency.

model selection regularization sparse models high-dimensional GIC

2023-09-04abs ↗pdf ↗

A Unified Regularization Approach to High-Dimensional Generalized Tensor Banditscs.LG

Unified approach tackles high-dimensional tensor bandits with convex optimization and weakly decomposable regularizers.

problem Challenges in high-dimensional generalized tensor bandits where existing algorithms fail.

method Proposes a generalized linear tensor bandits algorithm with a unified analytical framework using convex optimization and weakly decomposable regularizers.

result Unified analytical framework provides better bounds and broader applicability compared to existing methods.

tensor bandits convex optimization weakly decomposable regularizers high-dimensional data generalized linear models

2025-01-18abs ↗pdf ↗