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.

168,657 papers · 148 categories

Trend · papers per month

160320480640 · Jun 202019922001200920172026
48 results for Uniform-in-time Error Estimate

Improved error estimate for SGLD sampling algorithm.

problem Establishing a precise error bound for SGLD.
method Sharp uniform-in-time error estimate for SGLD under mild assumptions.
result Uniform-in-time O(η2)O(η^2) bound for KL-divergence between SGLD and Langevin diffusion.

Uniform-in-time analysis for Stein Variational Gradient Descent across various metrics.

problem Understanding long-term behavior of finite-particle systems in relation to their mean-field limits.
method Developed uniform-in-time propagation-of-chaos results for continuous-time SVGD using cutoff strategies and finite-dimensional theories.
result Uniform-in-time propagation-of-chaos bounds in various metrics, including Langevin kernel Stein discrepancy, Wasserstein-1, and Wasserstein-2 distances.

Uniform diffusion approximation for SGD in non-convex settings.

problem Finite-time diffusion approximation for SGD.
method Establishing uniform-in-time diffusion approximation with strong convexity and mild conditions.
result Uniform-in-time diffusion approximation of SGD without convexity of each loss function.

Improved particle approximation for mean-field neural networks.

problem Particle approximation error for mean-field neural networks.
method Improved particle approximation error by leveraging the problem structure in risk minimization.
result Established an LSI-constant-free particle approximation error concerning the objective gap.

Uniform bounds for neural network convergence without strong convexity assumptions.

problem Understanding the convergence of neural networks in the feature-learning regime.
method Establishing uniform-in-time weak propagation-of-chaos via mean-field deterministic Wasserstein-gradient-flow dynamics.
result Uniform bounds on the difference between infinite-width and finite-width neural network outputs, showing that fewer neurons can achieve a desired loss.

Study shows uniform-time chaos propagation in mean field Langevin dynamics.

problem Understanding the convergence of marginal distributions in mean field dynamics.
method Assumed functional convexity of energy, used LpL^p-convergence and Wasserstein metrics.
result Uniform-in-time propagation of chaos proved in both L2L^2-Wasserstein and relative entropy.

Develops a new algorithm for estimating model parameters using interacting particle systems.

problem Estimating parameters of latent variable models.
method Interacting Particle Langevin Algorithm (IPLA) based on Langevin diffusion.
result Nonasymptotic optimisation error bounds for the estimator.

We develop a framework for the analysis of deep neural networks and neural ODE models that are trained with stochastic gradient algorithms. We do that by identifying the connections between control theory, deep learning and theory of statistical sampling. We derive Pontryagin's optimality principle and study the corres…

2019-12-11abs ↗pdf ↗

Improved convergence rates for MFLD in various gradient estimators.

problem Proving convergence rates for mean-field Langevin dynamics with stochastic gradient updates.
method General framework for propagation of chaos, including finite-particle approximation, time-discretization, and stochastic gradient approximation.
result Improved convergence rates for SGD and SVRG settings.

New sampling algorithms for complex distributions without log-concavity.

problem Efficient sampling from complex, high-dimensional distributions.
method Randomized splitting Langevin Monte Carlo (RSLMC) algorithm.
result Uniform-in-time error bounds for RSLMC and RLMC algorithms.

Improved PoC for MFLD reduces approximation error and provides model ensemble guarantees.

problem Quantifying optimization complexity in mean-field Langevin dynamics.
method Refined defective log-Sobolev inequality for neural network training.
result Improved PoC result with reduced approximation error and theoretical model ensemble guarantees.

Optimized AIS scheme reduces bias and MSE for general proposals.

problem Performing Monte Carlo integration with general proposals.
method Global optimization of χ²-divergence using stochastic gradient Langevin dynamics.
result Explicit theoretical guarantees for uniform-in-time MSE reduction.

Stability result for a popular algorithm in optimal transport.

problem Stability of the Iterative Proportional Fitting Procedure in time and metric.
method Uniform stability analysis in the 1-Wasserstein metric.
result Quantitative stability result for entropy-regularized Optimal Transport and Schrödinger bridges.

Work on SGDm under heavy-tailed noise, revealing its generalization properties.

problem Understanding generalization of SGDm under heavy-tailed noise.
method Analysis of continuous-time limit (SDE) and discrete-time SGDm, establishing generalization bounds.
result SGDm can have worse generalization in the presence of heavy-tailed noise for quadratic loss functions.

In this paper we consider the class A\mathcal{A} of those solutions u(x,t)u(x,t) to the conjugate heat equation ddtu=Δu+Ru\frac{d}{dt}u = -Δu + Ru on compact Kähler manifolds MM with c1>0c_1 > 0 (where g(t)g(t) changes by the unnormalized Kähler Ricci flow, blowing up at T<T < \infty), which satisfy Perelman's differential Harnack i…

2006-01-17abs ↗pdf ↗

New algorithm for solving minimax problems over distributions converges to Nash equilibrium.

problem Solving minimax problems over probability distributions.
method Symmetric Mean-field Langevin Dynamics (MFL-AG and MFL-ABR) with weighted averaging and best response dynamics.
result Converges to mixed Nash equilibrium with average-iterate and last-iterate convergence.

Improved sampling from mean-field stationary distributions.

problem Sampling from the stationary distribution of mean-field SDEs.
method Decoupling the problem into two aspects: approximation of mean-field SDE and sampling from finite-particle distribution.
result Improved guarantees in various settings, including optimizing neural networks.

Optimizes calibration error estimators for better classifier trustworthiness.

problem Lack of guidance on selecting and tuning calibration error estimators.
method Reformulates calibration estimation as a regression problem with i.i.d. input pairs.
result Demonstrates the effectiveness of optimized calibration estimators on image classification tasks.

A new framework evaluates HTE estimators using relative error.

problem Lack of robust evaluation methods for HTE estimators.
method Proposes a relative error-based evaluation framework and neural network architecture to estimate nuisance parameters and robustly compare HTE estimators.
result Demonstrates reliable comparisons and improved HTE estimation through the proposed framework and learning algorithm.

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.

We introduce a unified framework for random forest prediction error estimation based on a novel estimator of the conditional prediction error distribution function. Our framework enables simple plug-in estimation of key prediction uncertainty metrics, including conditional mean squared prediction errors, conditional bi…

2019-12-16abs ↗pdf ↗

Estimates error for robust M-estimators with convex penalties.

problem Estimating out-of-sample error for robust M-estimators in high-dimensional linear regression.
method Proposes a generic out-of-sample error estimate for robust MM-estimators with convex penalties, using observed data and derivatives.
result The out-of-sample error estimate has a relative error of order n1/2n^{-1/2} under certain conditions.

The paper examines prediction and estimation risks of ridgeless least squares under general error assumptions.

problem Prediction and estimation risks of ridgeless least squares under realistic error structures.
method Analysis of prediction and estimation risks under general regression error assumptions, including clustered or serial dependence.
result The benefits of overparameterization extend to time series, panel, and grouped data.

Analysis of non-asymptotic estimation error and structured statistical recovery based on norm regularized regression, such as Lasso, needs to consider four aspects: the norm, the loss function, the design matrix, and the noise model. This paper presents generalizations of such estimation error analysis on all four aspe…

2015-05-09abs ↗pdf ↗

Wide neural networks learn features under μμP, identifying weights and decomposing support.

problem Feature learning in wide neural networks under μμP.
method Proving mean-field limit, characterizing identifiability, sparse-dictionary decomposition, and feature-learning-error decomposition.
result The triple (w,Dorb,S)(w^*, D^*_{\mathrm{orb}}, S^*) identifies the natural learning cell of the architecture-data pair (σ,ρ)(σ, ρ).

Paper introduces a new method for error estimation in classification tasks with limited data.

problem Challenges in designing accurate classifiers and evaluating their performance with limited training data.
method Introduces a novel Bayesian MMSE estimator for optimal Bayesian transfer learning (OBTL) using Monte Carlo importance sampling.
result Proposed OBTL error estimation scheme outperforms standard methods, especially in small-sample settings.

The study examines methods to correct measurement error in nutritional epidemiology studies.

problem Measurement error in nutritional studies leads to biased and underconfident estimates.
method The article reviews various bias-correction models for exposure variables in nutritional epidemiology.
result Bias-correction methods are essential for accurate inference in nutritional studies.

Error estimates found between SGD with momentum and Langevin diffusion.

problem Quantifying the difference between SGD with momentum and Langevin diffusion.
method Established error estimates using 1-Wasserstein and total variation distances.
result Quantitative error estimates between SGD with momentum and underdamped Langevin diffusion.

Data-driven method for error estimation without needing class complexity.

problem Constructing confidence intervals for a class of estimates.
method Data-driven approach to derive high-probability upper bounds on maximum error.
result Method naturally adapts to unknown correlation structures and works for finite and infinite classes.

Improved SGD bounds for machine learning models with Markovian noise.

problem Uniform high-probability bounds for SGD under PL condition with Markovian noise.
method Combining Poisson equation for Markovian noise and probabilistic induction for almost-sure bounds.
result Matching 1/k1/k decay rate for expected suboptimality.

Robust estimators for Gaussian sparse tasks with optimal error under contamination.

problem Robust mean estimation, PCA, and linear regression in the presence of Huber contamination.
method Novel multidimensional filtering method for sparse regime.
result Optimal error guarantees within constant factors for Gaussian robust kk-sparse mean estimation.

This paper develops a bootstrap method to estimate errors in Random Fourier Features.

problem Inability to estimate the error of Random Fourier Features approximations.
method Develops a bootstrap approach to numerically estimate the errors of RFF approximations.
result Specific, flexible, and adaptive error estimates for RFF approximations.

Proposes a new calibration error estimator for deep neural networks.

problem Improves calibration of deep neural networks, especially for canonical calibration.
method Uses a Dirichlet kernel density estimate to create a low-bias, trainable calibration error estimator.
result Asymptotically converges to true LpL_p calibration error, enabling efficient estimation and mini-batch updates.