We provide a nonasymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) to a target measure in Wasserstein-2 distance without assuming log-concavity. Our analysis quantifies key theoretical properties of the SGHMC as a sampler under local conditions which significantly improves…
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
48 results for “Nonasymptotic Convergence”
Fast Incremental Expectation Maximization for finite-sum optimization: nonasymptotic convergencecs.LG
FIEM accelerates EM for large datasets with nonasymptotic convergence bounds.
problem Efficiently optimizing large datasets using EM framework.
method FIEM recasts EM in Stochastic Approximation framework and provides nonasymptotic convergence bounds.
result Nonasymptotic bounds for convergence in expectation as a function of and $\kmax$.
ROOT-SGD solves convex optimization problems with optimal nonasymptotic and near-optimal asymptotic performance.
problem Solving strongly convex and smooth unconstrained optimization problems using stochastic first-order algorithms.
method ROOT-SGD: Recursive One-Over-T SGD, averaging past stochastic gradients.
result Achieves state-of-the-art performance in both nonasymptotic and asymptotic senses.
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.
Gradient descent optimally trains RNNs without overparameterization.
problem Training recurrent neural networks (RNNs) with gradient descent.
method Nonasymptotic analysis of gradient descent for RNNs with diagonal weight matrices.
result Gradient descent can achieve optimality in RNNs with a network size scaling logarithmically with the number of samples.
Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows SGLD to escape local minima and suffices to guarantee asymptotic convergence to g…
We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of one stochastic smooth term and multiple stochastic nonsmooth terms. In each iteration, our splitting t…
New confidence intervals improve treatment effect estimation in randomized experiments.
problem Improving confidence intervals for treatment effects in randomized experiments.
method Systematic exploitation of negative dependence or variance adaptivity.
result Achieved nonasymptotic confidence intervals with the same effective sample size as asymptotic ones.
We establish the first nonasymptotic error bounds for Kaplan-Meier-based nearest neighbor and kernel survival probability estimators where feature vectors reside in metric spaces. Our bounds imply rates of strong consistency for these nonparametric estimators and, up to a log factor, match an existing lower bound for c…
On the Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Costcs.LG
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus o…
The paper improves nonparametric confidence bands for band-limited functions.
problem Constructing nonparametric simultaneous confidence bands with nonasymptotic and distribition-free guarantees.
method Based on Paley-Wiener reproducing kernel Hilbert spaces, the paper relaxes assumptions, improves noise estimation, and tightens constraints.
result Enhanced confidence bands with improved efficiency and tighter constraints.
Gaining Outlier Resistance with Progressive Quantiles: Fast Algorithms and Theoretical Studiesstat.ME
New framework robustifies loss functions with quantiles for outlier resistance.
problem Widespread outliers in big data affect statistical estimation and inference.
method Introduces a framework connecting to trimming, scalable algorithms, and new techniques.
result Robust estimators achieve minimax rate optimality in regression, classification, and neural networks.
We take a Hamiltonian-based perspective to generalize Nesterov's accelerated gradient descent and Polyak's heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Euclidean and non-Euclidean normed vector spaces. Our perspective leads to a generic and unifying non…
New convergence rates found for PnP methods using MMSE denoisers.
problem Asymptotic convergence of PnP methods with MMSE denoisers.
method Explicitly represented MMSE denoiser as an upper Moreau envelope, derived sublinear convergence rates.
result First sublinear convergence guarantee for PnP proximal gradient descent with MMSE denoiser.
New inequalities for matrix supermartingales converge under various conditions.
problem Convergence and maximal inequalities of supermartingales in positive semidefinite matrices.
method Developed new concentration inequalities for matrix supermartingales.
result New inequalities for matrix supermartingales under different tail conditions.
This paper tightens the law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
problem Developing nonasymptotic concentration bounds for empirical KL_inf with optimal constants and rates.
method Presenting a tight law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
result A tight law of the iterated logarithm for empirical KL_inf, applicable to unbounded data.
This paper introduces time-uniform CLT-based confidence intervals for statistical inference.
problem Developing valid statistical inference methods for sequential data.
method Time-uniform central limit theory and strong invariance principles.
result Asymptotic confidence sequences (CSs) that are uniformly valid over time.
Large sectors of the recent optimization literature focused in the last decade on the development of optimal stochastic first order schemes for constrained convex models under progressively relaxed assumptions. Stochastic proximal point is an iterative scheme born from the adaptation of proximal point algorithm to nois…
In this paper, we are concerned with a non-asymptotic analysis of sampling algorithms used in nonconvex optimization. In particular, we obtain non-asymptotic estimates in Wasserstein-1 and Wasserstein-2 distances for a popular class of algorithms called Stochastic Gradient Langevin Dynamics (SGLD). In addition, the afo…
New method estimates gradients accurately with sharp bounds.
problem Accurate gradient estimation in regression problems.
method Nearest-neighbor based pointwise estimate of gradients.
result Sharp nonasymptotic bounds for gradient estimation.
In this work, we study the problem of reconstructing shapes from simple nonasymptotic densities measured only along shape boundaries. The particular density we study is also known as the integral area invariant and corresponds to the area of a disk centered on the boundary that is also inside the shape. It is easy to s…
Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is understood mainly in the setting of smooth (gradient-Lipschitz) log-densities, a seri…
In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling. We investigate the nonasymptotic convergence of AGLD with a unified analysis for different data accessing (e.g. random access, cyclic access and random reshuffle) and snapshot upd…
New methods for estimating complex causal effects in econometrics.
problem Estimating causal parameters in short panel data models using nested nonparametric instrumental variable regression.
method Introducing techniques to limit ill-posedness in nested NPIV, providing explicit mean square rates and efficient inference.
result Explicit mean square rates for nested NPIV and efficient inference for causal parameters.
We consider nonconvex-concave minimax problems, , where is nonconvex in but concave in and is a convex and bounded set. One of the most popular algorithms for solving this problem is the celebrated…
Nonparametric, Nonasymptotic Confidence Bands with Paley-Wiener Kernels for Band-Limited Functionsstat.ML
The paper creates nonparametric confidence bands for band-limited functions.
problem Estimating confidence bands for band-limited functions with finite samples and unknown noise.
method Uses Paley-Wiener reproducing kernel Hilbert spaces and gradient-perturbation methods.
result Non-asymptotic guarantees for confidence regions without assuming a parametric model.
KIPLMC methods improve statistical inference in latent variable models.
problem Statistical inference in latent variable models.
method Joint diffusion process in parameter and latent variable spaces, with two explicit discretizations.
result KIPLMC methods achieve accelerated convergence rates in Wasserstein-2 distance.
Study on signal detection in sparse additive models with nonasymptotic minimax rates.
problem Signal detection in sparse additive models.
method Nonasymptotic minimax analysis of signal detection in sparse additive models.
result Established minimax separation rate for signal detection.
Early stopping improves logistic regression's calibration and consistency in high dimensions.
problem Improving the statistical performance of gradient descent in overparameterized logistic regression.
method Investigates the effects of early stopping on gradient descent in logistic regression.
result Early-stopped gradient descent is well-calibrated and statistically consistent, while asymptotic gradient descent is not.
New method approximates sampling from smooth potential distributions using a vanishing penalty.
problem Sampling from smooth potential distributions on high-dimensional spaces.
method Penalized Langevin dynamics (PLD) with vanishing penalty.
result Established upper bound on Wasserstein-2 distance for PLD approximation.
Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisationstat.ML
The paper shows how label noise in training can lead to solutions that solve a Lasso program.
problem Understanding the implicit bias of training algorithms in overparametrised models.
method Analyzing the continuous time version of the training dynamics of a quadratically parametrised model.
result The stochastic flow implicitly solves a Lasso program, providing convergence guarantees and support recovery conditions.
Sparse principal component analysis (PCA) is an important technique for dimensionality reduction of high-dimensional data. However, most existing sparse PCA algorithms are based on non-convex optimization, which provide little guarantee on the global convergence. Sparse PCA algorithms based on a convex formulation, for…
Confidence Interval Construction and Conditional Variance Estimation with Dense ReLU Networksstat.ML
Paper improves confidence intervals and variance estimation for deep learning models.
problem Improving confidence intervals and variance estimation in deep learning models.
method Residual-based framework for conditional variance estimation; robust bootstrap procedure for confidence intervals.
result First non-asymptotic bounds for variance estimation using ReLU networks.
New algorithm improves stability and efficiency of neural network training.
problem Stability and efficiency issues in adaptive optimization for neural networks.
method Polygonal approximations for SDEs with monotone coefficients, providing stability and addressing vanishing gradients.
result TheoPouLa algorithm shows superior performance over popular adaptive optimizers.
Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling from a given distribution is impossible or computationally expensive and, there…
Many modern big data applications feature large scale in both numbers of responses and predictors. Better statistical efficiency and scientific insights can be enabled by understanding the large-scale response-predictor association network structures via layers of sparse latent factors ranked by importance. Yet sparsit…
Study confirms optimal minimax rate for nonlocal interaction kernel estimation.
problem Estimating nonlocal interaction kernels in interacting particle systems.
method Introduced tamed least squares estimator (tLSE) achieving optimal convergence rate.
result Optimal minimax rate of convergence confirmed for .
Binacox: automatic cut-point detection in high-dimensional Cox model with applications in geneticsstat.ML
We introduce the binacox, a prognostic method to deal with the problem of detecting multiple cut-points per features in a multivariate setting where a large number of continuous features are available. The method is based on the Cox model and combines one-hot encoding with the binarsity penalty, which uses total-variat…
A theorem for debiasing machine learning with finite sample guarantees.
problem Calculating confidence intervals for machine learning functionals.
method Debiased machine learning based on bias correction and sample splitting.
result Nonasymptotic debiased machine learning theorem with finite sample guarantees.
New theory explains how overparametrized neural networks generalize well without bias-variance trade-off.
problem Overparametrized neural networks generalize well despite classical bias-variance trade-off.
method Nonasymptotic generalization theory for two-layer neural networks with ReLU activation, incorporating scaled variation regularization.
result Prediction bounds for all network widths reproduce the double descent phenomenon, and overparametrized models are nearly minimax optimal.
The paper investigates heavy-tailed behavior in offline SGD, showing it approximates power-law tails.
problem Understanding heavy-tailed behavior in offline (multi-pass) SGD with finite data.
method Proves nonasymptotic Wasserstein convergence bounds for offline SGD to online SGD.
result Offline SGD exhibits approximate power-law tails as the number of data points increases.
Study Q-learning with averaging for reinforcement learning, proving efficient inference and error bounds.
problem Efficient inference and error bounds for Q-learning with averaging.
method Functional central limit theorem and asymptotic linear estimator for optimal Q-value function.
result Standardized partial-sum process converges weakly to a rescaled Brownian motion, matching instance-dependent lower bound for error.
Proposes estimators for complex dose-response curves using kernel methods.
problem Estimating complex dose-response curves with continuous treatments, mediators, and covariates.
method Kernel ridge regression with sequential kernel embedding technique.
result Simple estimators for mediated and time-varying dose response curves with nonasymptotic uniform rates.
High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexitymath.ST
Although the standard formulations of prediction problems involve fully-observed and noiseless data drawn in an i.i.d. manner, many applications involve noisy and/or missing data, possibly involving dependence, as well. We study these issues in the context of high-dimensional sparse linear regression, and propose novel…
LinUCB algorithm handles adaptive sampling biases for linear bandits.
problem Adaptive sampling introduces biases in statistical inference.
method LinUCB algorithm with stability property for linear bandits.
result LinUCB achieves asymptotic normality with Wald-type confidence sets.
This paper improves causal inference using deep neural networks for low-dimensional covariates.
problem Improving causal inference with deep learning for high-dimensional covariates.
method Doubly robust off-policy learning with deep neural networks on low-dimensional manifolds.
result Nonasymptotic regret bounds for finite- and continuous-action scenarios, converging at a fast rate depending on intrinsic manifold dimension.
RFM uses tangent vector fields to match data on manifolds, analyzing TV convergence for Euler discretization.
problem Matching data on curved manifolds using flow-based models.
method Developed a nonasymptotic TV convergence analysis for RFM samplers using Euler discretization.
result Explicit bounds on TV convergence separating numerical discretization and learning errors.
Method solves nonconvex constrained optimization problems with a new augmented Lagrangian approach.
problem Nonconvex composite functional constraints with inequality constraints.
method First-order augmented Lagrangian method with smoothed prox-linear reformulation.
result Explicit convergence rates for the proposed method in terms of KKT residual.