Research
On-device research index

arXiv research

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

169,341 papers · 148 categories

Trend · papers per month

1122 · Sep 201719922001200920182026
36 results for dimensionality-dependent

The paper derives tighter generalization bounds for kk-dimensional coding schemes in finite-dimensional feature spaces.

problem Previous bounds for kk-dimensional coding schemes were dimensionality-independent and not suitable for finite-dimensional data.
method The paper derives a dimensionality-dependent generalization bound for kk-dimensional coding schemes by bounding the covering number of the loss function class induced by the reconstruction error.
result The derived bound is tighter than previous results and converges faster, especially for finite-dimensional data.

Improved KL bounds and Wasserstein guarantees for diffusion flow matching under minimal conditions.

problem Theoretical convergence properties of Brownian motion based diffusion flow matching.
method Refined analysis under Kullback-Leibler and 2-Wasserstein distances.
result State-of-the-art scaling in KL convergence bounds under minimal conditions.

The paper develops a method to model high-dimensional data with many variables and weak signals.

problem Modeling high-dimensional dependent data with many explanatory variables and low signal-to-noise ratio.
method Penalized regression for high-dimensional data, factor modeling of residuals, high-dimensional white noise testing, projected Principal Component Analysis.
result Established asymptotic properties of the proposed method for high-dimensional data.

New method optimizes portfolios with options, addressing asymmetry, dimensionality, and dependence.

problem Optimizing portfolios with options, especially when distributions are asymmetric, dimensions are high, and payoffs are dependent.
method Developed a new dependency matrix based on conditional probabilities of options' payoffs, computed using copula structures.
result Empirical evidence shows the approach is efficient, fast, and scalable to large portfolios of options.

Overview of high-dimensional time series regression methods.

problem Estimation and inference with high-dimensional time series data.
method Limit theory for high-dimensional dependent data, asymptotic theory for time series regression, statistical learning methods.
result Main limit theory results and asymptotic theory for high-dimensional time series regression.

This paper attempts to investigate the space of various characteristic classes for smooth manifold bundles with local system on the total space inducing a finite holonomy covering. These classes are known as twisted higher torsion classes. We will give a system of axioms that we require these cohomology classes to sati…

2012-11-16abs ↗pdf ↗

Random Fourier Features reduce kernel matrix reconstruction error without dimensionality dependence.

problem Error reduction in kernel matrix reconstruction for high-dimensional data.
method Random Fourier Features with theoretical error bounds.
result Error probability is independent of data dimensionality.

New bounds show BBVI's gradient variance matches SGD conditions, improving parameterization efficiency.

problem Understanding and improving the convergence of black-box variational inference (BBVI).
method Showed BBVI satisfies matching gradient variance bounds corresponding to the ABC condition for smooth and quadratically-growing log-likelihoods.
result Proven BBVI's gradient variance matches SGD conditions, with superior dimensional dependence for mean-field parameterization.

This work develops a neural network approach to learn vine copula models for better synthetic data generation.

problem The challenge of selecting the best vine copula model with exponential configurations.
method Formulated a vine structure learning problem with vector and reinforcement learning representations, used neural networks to find embeddings for the best vine model.
result The proposed approach generates models with better log-likelihood and produces high-quality synthetic samples.

The study sets limits on how well systems can be controlled adaptively.

problem Learning to control unknown linear Gaussian systems with quadratic costs.
method Combining ideas from experiment design, estimation theory, and perturbation bounds of information matrices.
result Regret lower bounds of the order of T\sqrt{T} in the time horizon TT accurately capture control-theoretic parameters.

We consider learning continuous probabilistic graphical models in the face of missing data. For non-Gaussian models, learning the parameters and structure of such models depends on our ability to perform efficient inference, and can be prohibitive even for relatively modest domains. Recently, we introduced the Copula B…

2012-03-15abs ↗pdf ↗

Enhanced multivariate GARCH model using LSTM for better volatility forecasting.

problem Limitations of traditional multivariate GARCH in capturing persistent volatility and co-movement.
method Integrates deep learning (LSTM) into multivariate GARCH models to capture nonlinear and dynamic dependence structures.
result Superior out-of-sample portfolio risk forecast compared to traditional methods.

VADD enhances discrete diffusion models by capturing inter-dimensional correlations, improving sample quality.

problem Limited modeling of inter-dimensional dependencies in MDMs degrades performance with few denoising steps.
method Introduces an auxiliary recognition model for latent variable modeling, enabling stable training via variational lower bounds maximization and amortized inference.
result VADD consistently outperforms MDM baselines in sample quality with few denoising steps.

Differentially private hyperparameter tuning improves privacy in machine learning.

problem Hyperparameter tuning leaks private information through selected configurations.
method Local Bayesian optimization using Gaussian Process surrogate for private gradient approximation.
result DP-GIBO converges to locally optimal hyperparameters with polynomial dimensional dependence.

Sharp estimates for Struwe's decomposition in various dimensions.

problem Quantifying the distance of functions to sums of Talenti bubbles.
method Developed new quantitative estimates for the distance of functions to the manifold of sums of Talenti bubbles in different dimensions.
result Sharp quantitative estimates for the distance of functions to sums of Talenti bubbles in various dimensions.

A new test for conditional independence adapts to nonlinear dependencies efficiently.

problem Testing conditional independence in nonlinear and high-dimensional data.
method Nearest-neighbor estimator of conditional mutual information combined with local permutation scheme.
result The test reliably simulates null distribution and is better calibrated for non-smooth densities.

A new random forest algorithm improves tree construction for optimal performance.

problem Improving the performance of random forests, especially in complex and smooth scenarios.
method Adaptive split-balancing method using permutation-based splitting criterion.
result Achieves minimax optimality under various Lipschitz and Hölder classes.

New framework calibrates computer models using deep learning and quantile regression.

problem Uncertainty in computer model input parameters due to high-dimensional time series data.
method Deep neural network with long-short term memory layers for inverse modeling, quantile regression for interval predictions.
result Accurate point and interval estimates for input parameters in WRF-hydro model.

The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.

problem Theoretical guarantees for score-mismatched diffusion models in zero-shot conditional sampling.
method Theoretical analysis of score-mismatched diffusion models and zero-shot conditional samplers.
result Theoretical performance guarantees with explicit dimensional dependencies for score-mismatched diffusion samplers.

SMART-FAN-Lasso fine-tunes neural networks for high-dimensional nonparametric regression.

problem Fine-tuning neural networks for high-dimensional nonparametric regression with variable selection.
method Source-model-augmented residual tuning (SMART) framework for neural Lasso.
result SMART-FAN-Lasso achieves statistical acceleration over single-task learning under precise conditions.

New framework for identifying spatial data components using TP latent components.

problem Identifying complex dependencies in spatial data.
method Introduces a new nonlinear ICA framework with tt-process latent components and develops a learning and inference algorithm.
result Identifiability of TP independent components under general conditions and Gaussian Process limit.

Paper presents ACLIME-ADMM for efficient structure learning in high-dimensional physical processes.

problem Learning dependencies in high-dimensional physical processes modeled by PDEs.
method ACLIME-ADMM, a two-step algorithm using ADMM for adaptive structure learning.
result ACLIME-ADMM efficiently recovers structure in real atmospheric data, including wind direction switches.

AdaGrad outperforms SGD in non-convex optimization problems by a factor of d.

problem Finding near-stationary points in stochastic non-convex optimization.
method Refined assumptions on smoothness and gradient noise variance, l1l_1-norm stationarity measure.
result AdaGrad achieves a convergence rate favorable over SGD in certain non-convex settings.