The CLT fails for LLM evaluations with small data, leading to underestimation of uncertainty.
problem Inaccurate uncertainty estimates in LLM evaluations with small datasets.
method Alternative frequentist and Bayesian methods for uncertainty quantification.
result CLT-based methods underestimate uncertainty in small data settings.
Paper studies CLT rates for dependent data in Wasserstein-p distance.
problem CLT rates for multivariate dependent data in Wasserstein-p distance.
method Analyzes locally dependent sequences and geometrically ergodic Markov chains.
result Establishes optimal W 1 W_1 W 1 CLT rates and W p W_p W p ( p ≥ 2 p\ge 2 p ≥ 2 ) rates for dependent data. New CLT for SGD in high-dimensional regression provides online inference.
problem Quantifying uncertainty in SGD for high-dimensional regression.
method Established a high-dimensional CLT for online SGD iterates.
result Developed an online approach for estimating variance in CLT.
Develops CLTs for Markov chain transition probabilities and policies.
problem Estimating transition probabilities and policies in controlled Markov chains.
method Non-parametric estimator for transition matrices; CLTs for value, Q-, and advantage functions; goodness-of-fit tests.
result Asymptotic normality of estimators under specific logging policies.
The paper establishes CLTs for Markov chains and improves sampling algorithms for heavy-tailed distributions.
problem Establishing central limit theorems for ergodic averages of Markov chains.
method Drift conditions to provide necessary and sufficient conditions for CLTs, including lower bounds on convergence rates.
result Sharp conditions and convergence rates for various MCMC algorithms on heavy-tailed targets.
Gradient descent dynamics in wide neural networks are analyzed using a dynamical CLT.
problem Understanding the fluctuations in wide shallow neural networks trained via gradient descent.
method Dynamical Central Limit Theorem (CLT) applied to neural network dynamics.
result Asymptotic fluctuations remain bounded in mean square throughout training.
Paper analyzes CLT for TTSA with Markovian noise, broadening its applications.
problem Analyzing asymptotic behavior of TTSA under Markovian noise.
method Central Limit Theorem applied to TTSA with Markovian noise.
result Uncovered coupled dynamics of TTSA influenced by Markov chain.
Study on kernel tests for high-dimensional data, focusing on MMD and CLT.
problem Asymptotic behavior of kernel two-sample tests in high dimensions and large samples.
method Maximum mean discrepancy (MMD) with isotropic kernels, deriving asymptotic expansions and CLT.
result Interplay between moment discrepancy and dimension-and-sample orders in kernel tests.
Characterizes UCB algorithm performance in bandit problems.
problem Optimizing UCB algorithm performance in stochastic bandit environments.
method Novel perturbation analysis to characterize CLT of pulls and means.
result Smooth interpolation of pseudo-regret between large and small gap regimes.
We show that when a spacetime M ( = M ∪ ∂ M ) \mathcal{M}(=M \cup \partial M) M ( = M ∪ ∂ M ) is globally hyperbolic with (possibly empty) smooth timelike boundary ∂ M \partial M ∂ M , a metrizable topology, the closed limit topology (CLT) introduced by F. Hausdorff himself in the 1950's in set theory, can be advantageously adopted on the Geroch-Kronheime…
Polyak-Ruppert CLT for SA-Adam with momentum and non-convergent adaptive preconditioning
problem Adaptive optimizers combining momentum and non-convergent preconditioning
method Proving positive drift stability and a non-autonomous Polyak-Ruppert CLT for SA-Adam
result The iterate-marginal covariance is exactly the plain stochastic gradient descent (SGD) sandwich
We provide non-asymptotic convergence rates of the Polyak-Ruppert averaged stochastic gradient descent (SGD) to a normal random vector for a class of twice-differentiable test functions. A crucial intermediate step is proving a non-asymptotic martingale central limit theorem (CLT), i.e., establishing the rates of conve…
Unified treatment of CLTs for Lévy models across physics, finance, and econometrics.
problem Understanding convergence of stochastic integrals in Lévy models.
method Unified weak convergence results for Skorokhod spaces J1 and M1.
result General principles apply to specific settings, yielding new insights.
This paper studies convergence properties of multivariate distributions constructed by endowing empirical margins with a copula. This setting includes Latin Hypercube Sampling with dependence, also known as the Iman--Conover method. The primary question addressed here is the convergence of the component sum, which is r…
Quantitative CLTs show neural network distributions converge to Gaussian as width increases.
problem Understanding the distribution of fully connected neural networks with random weights and biases.
method Analyzing the distribution of a fully connected neural network with random Gaussian weights and biases, proving quantitative bounds on normal approximations.
result The distance between a random fully connected network and the corresponding infinite width Gaussian process scales like n − γ n^{-γ} n − γ for γ > 0 γ>0 γ > 0 . 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.
Random walks on metric spaces embed quasi-isometrically into the space.
problem Embedding random subgroups of metric spaces quasi-isometrically.
method Analyzing random walks and contracting elements in metric spaces.
result Random subgroups of isometry groups are quasi-isometrically embedded.
The study proves a quantitative functional CLT for neural networks with smooth activation functions.
problem Understanding the convergence rates of neural networks with different activation functions.
method Functional versions of the Stein-Malliavin approach and a quantitative functional central limit theorem.
result Rates of convergence depend on the smoothness of the activation function, ranging from logarithmic to sqrt(n).
This paper strengthens the central limit theorem for order statistics using relative entropy.
problem Establishing a stronger mode of convergence for central limit behavior of order statistics.
method Using relative entropy to ensure a stronger mode of convergence for central limit behavior of order statistics.
result An order O ( 1 / n ) O(1/\sqrt{n}) O ( 1/ n ) rate of convergence is established under mild conditions. Paper derives CLT for Bayesian neural networks trained with variational inference.
problem Analyzing the fluctuation behavior of Bayesian neural networks trained with different variational inference schemes.
method Rigorous derivation of CLT for three variational inference schemes: idealized, Bayes-by-Backprop, and Minimal VI.
result Minimal VI scheme has larger variances but is more computationally efficient.
New bounds show current methods overestimate system parameter errors.
problem Current bounds overestimate parameter errors in system identification.
method Utilized asymptotic normality and second-order decomposition.
result Obtained finite-sample bounds matching optimal rates up to constants.
The paper explores how dynamic preconditioning affects the CLT in online averaging.
problem When does dynamic preconditioning preserve the Polyak-Ruppert CLT?
method The authors decompose the averaged error and identify a stabilization-rate threshold for the CLT to hold.
result The CLT holds if the dynamic remainder vanishes in L 2 L^2 L 2 and the stabilization rate exceeds a threshold. Symmetry in neural networks affects generalization, as shown by CLT and RG transformations.
problem Improving generalization in neural networks by incorporating physical symmetries.
method Evaluation of symmetry constraints and expressivity in MLPs and GNNs using the CLT as a test case.
result Overly complex or overconstrained models generalize poorly, revealing a competition between symmetry constraints and expressivity.
Study on stochastic approximation with Polyak-Ruppert averaging for linear systems.
problem Understanding the asymptotic and non-asymptotic properties of stochastic approximation procedures.
method Detailed analysis of linear stochastic approximation with Polyak-Ruppert averaging, focusing on asymptotic and non-asymptotic properties.
result Proves CLT and non-asymptotic concentration inequality for averaged iterates, providing refined understanding of linear stochastic approximation.
New OLO algorithms use Stein's method for better performance tradeoffs.
problem Achieving optimal tradeoffs in adversarial online linear optimization.
method Operationalizing Stein's method for computationally efficient OLO algorithms.
result Additively sharp upper bounds on regret and total loss.
Unified framework for statistical inference in gradient boosting regression.
problem Challenges in statistical inference and uncertainty quantification for gradient boosting.
method Integrates dropout or parallel training with regularization for CLT in boosting.
result Increasing dropout rate and parallel trees enhances signal recovery and performance.
Study small-time CLTs for stochastic Volterra equations with various kernels.
problem Understanding the behavior of stochastic Volterra equations with different kernels.
method Proved convergence of finite-dimensional distributions, functional CLT, and limit theorems for smooth transformations.
result Derived asymptotic pricing formulae for digital calls in rough volatility models.
New bounds for SGD in high dimensions improve inference efficiency.
problem Quantifying uncertainty in high-dimensional SGD.
method Established non-asymptotic Berry--Esseen bounds for online least-squares SGD.
result Gaussian Central Limit Theorem holds for t ≳ d 1 + δ t \gtrsim d^{1+δ} t ≳ d 1 + δ , extending dimensional scaling. New method for uncertainty analysis in TabPFN, a state-of-the-art tabular transformer.
problem No method for uncertainty decomposition in TabPFN.
method Casted as a Bayesian predictive inference problem, derived variance estimators using predictive CLT.
result Fast to compute credible bands that target epistemic uncertainty and achieve near-nominal frequentist coverage.
New CLT for AIPW estimator in high-dimensional settings.
problem Estimating ATE in high-dimensional covariate scenarios.
method Cross-fitting AIPW estimator with well-specified models.
result Established a new CLT for the scaled cross-fit AIPW.
The paper analyzes SGD with dropout regularization in linear models, proving asymptotic properties and providing inference tools.
problem Analyzing the behavior of SGD with dropout regularization in linear models.
method Establishing geometric-moment contraction (GMC) and proving quenched central limit theorems (CLT).
result The existence of a unique stationary distribution and asymptotic normality results for SGD with dropout.
Paper proposes a new UCB approach for estimating maximum mean.
problem Estimating the maximum mean in various applications.
method Upper Confidence Bound (UCB) approach with adaptive sampling.
result LSA estimator shows faster bias decay compared to GA.
Develops a Monte Carlo algorithm for tempered stable process extrema.
problem Calculating the extrema of exponentially tempered Lévy processes.
method Novel Monte Carlo algorithm based on increments of the process.
result Geometrically fast convergence and optimal computational complexity.
The paper analyzes Kernel Density Estimation in high dimensions with varying data and dimensionality.
problem High-dimensional Kernel Density Estimation with growing data and dimensionality.
method Examines the behavior of Kernel Density Estimators in the regime where both data points and dimensionality grow with a fixed ratio.
result Three distinct statistical regimes are identified for Kernel-based density estimates, each with different statistical properties.
We establish decoupled functional CLTs for two-time-scale stochastic approximation.
problem Understanding the asymptotic behavior of two-time-scale stochastic approximation.
method Martingale problem approach and auxiliary sequence.
result The limiting dynamics of two-time-scale SA are independent of each other.
New method assesses multivariate stochastic dominance using Optimal Transport.
problem Benchmarking models across multiple metrics considering dependencies.
method Characterization of multivariate first stochastic dominance via couplings, entropic regularization, and Optimal Transport.
result Established CLT and consistency for the empirical statistic, enabling hypothesis testing.
We obtain a Central Limit Theorem for closed Riemannian manifolds, clarifying along the way the geometric meaning of some of the hypotheses in Bhattacharya and Lin's Omnibus Central Limit Theorem for Fréchet means. We obtain our CLT assuming certain stability hypothesis for the cut locus, which always holds when the ma…
Bootstrap method for Markov chains in reinforcement learning.
problem Distributional consistency in finite controlled Markov chains with unknown control policies.
method Model-based bootstrap with novel LLN and CLT for visitation counts and transition increments.
result Asymptotically valid confidence intervals for value and Q Q Q -functions in offline RL. The paper studies a rebalanced dataset for imbalanced classification using Centered Random Forests.
problem Imbalanced classification where one class is underrepresented.
method Theoretical analysis of Centered Random Forests (CRF) with rebalanced datasets and debiasing techniques.
result Theoretical Central Limit Theorem (CLT) for the infinite CRF and debiased estimator IS-ICRF.
NAST generalizes scattering transform for non-stationary time series analysis.
problem Analyzing non-stationary time series data.
method Neural activation of scattering transform with various activation functions and high pass filters.
result Central and non-central limit theorems for NAST of Gaussian processes.
The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the classical central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic diff…
Paper proves CLT for quantile SGD with constant learning rate.
problem Quantile estimation via SGD with non-smooth, non-strongly convex loss.
method Viewed as a Markov chain, derived stationary distribution, analyzed MGF, proved CLT.
result Centered and standardized stationary distribution converges to Gaussian as η i g h t a r r o w 0 η
ightarrow0 η i g h t a r r o w 0 . Proves CLT for Brownian paths on pinched negative curvature manifolds.
problem Distribution of Brownian paths on pinched negative curvature manifolds.
method Proof of central limit theorem for distances and Green functions.
result Central limit theorem holds for Brownian paths in pinched negative curvature.
Study mini-batch SGD noise and its limits, proving complexity guarantees.
problem Analyzing the noise in mini-batch SGD and its impact on optimization.
method Examined the conditional covariance and diffusion limits of SGD under different sampling designs.
result Proved mean-square upper bounds and Fisher van Trees lower bounds for SGD, linking them to effective dimension and condition number.
Paper proves CLTs for Q-learning with asynchronous updates.
problem Establishing convergence rates for Q-learning algorithms.
method Polyak-Ruppert averaging, non-asymptotic and functional CLTs.
result Convergence rates in Wasserstein distance for Q-learning.
The paper provides rigorous guarantees for m-out-of-n bootstrap estimators of sample quantiles.
problem Lack of parameter-free guarantees for robust inference with heavy-tailed data.
method Central limit theorem and Edgeworth expansion for m-out-of-n bootstrap estimators of sample quantiles.
result Established rigorous guarantees for the soundness of m-out-of-n bootstrap estimators of sample quantiles.
The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochast…
New method for constructing confidence intervals for time series data.
problem Constructing confidence intervals for statistical functionals from time series data.
method Proposes a general purpose confidence interval procedure based on overlapping batches of time series data.
result Large overlapping batches yield confidence intervals of higher quality than generic methods.