Statistical Inference for Stochastic Gradient Descent Beyond Finite Variance

• URL: http://arxiv.org/abs/2605.26000v1
• Date: Mon, 25 May 2026 16:18:39 GMT
• Title: Statistical Inference for Stochastic Gradient Descent Beyond Finite Variance
• Abstract summary: gradient descent (SGD) is a foundational algorithm for large-scale statistical learning and optimization.<n>We develop an efficient, model-agnostic methodology for constructing confidence regions from SGD trajectories.
• Score: 10.36372217426986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stochastic gradient descent (SGD) is a foundational algorithm for large-scale statistical learning and stochastic optimization. However, statistical inference based on SGD iterates remains challenging when stochastic gradients have infinite variance, as the relevant limiting distributions depend on unknown nuisance parameters. In this paper, we develop an efficient, model-agnostic methodology for constructing confidence regions from SGD trajectories that applies in both finite- and infinite-variance regimes. The procedure is based on a joint weak convergence result for the Polyak-Ruppert averaged estimator and an empirical second-moment normalizer constructed from stochastic gradients along the SGD trajectory. This joint limit yields a self-normalized statistic in which the leading tail-dependent scaling terms cancel. We then use a subsampling calibration scheme to estimate the relevant critical values, avoiding explicit estimation of tail indices, slowly varying functions, or stable-law parameters. The resulting confidence regions are straightforward to implement and are asymptotically valid under both the finite- and infinite-second-moment regimes. Simulation studies show reliable coverage in various settings, supporting the proposed method as a practical tool for uncertainty quantification in stochastic optimization.

Related papers

• Statistical Inference on Gradient Flows [46.05870703588429]
  We develop a theory for time-uniform statistical inference on gradient flows arising from empirical risk minimization.<n>We introduce an algorithm-aware covariance estimator that evolves jointly with the gradient flow and avoids matrix inversion, resampling, or sample splitting.<n>Our results connect optimization dynamics with statistical inference and provide practical tools for uncertainty quantification in gradient-based methods.
  arXiv  Detail & Related papers  (2026-05-31T14:22:37Z)
• Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo [7.029571020570523]
  We propose new discrete-time approximations to SG(L)D with and without momentum.<n>We prove quantitative, non-asymptotic error bounds showing that these estimates are sufficiently accurate for practical tuning and uncertainty quantification.
  arXiv  Detail & Related papers  (2026-05-29T19:24:38Z)
• TRSVR: An Adaptive Stochastic Trust-Region Method with Variance Reduction [17.083793956698994]
  We propose a trust method for unconstrained non-reduced optimization that incorporates variance-region (SVRG) to accelerate convergence.<n>The proposed algorithm relies solely on gradient information and does not require function value evaluations.
  arXiv  Detail & Related papers  (2026-01-21T04:41:57Z)
• Derivative-Free Sequential Quadratic Programming for Equality-Constrained Stochastic Optimization [3.2489082010225485]
  We consider solving nonlinear optimization problems with an objective and deterministic equality constraints.<n>We propose a Derivative-Free Sequential Quadratic Programming (DF-SSQP) method.<n>Under standard assumptions, we establish the global almost-sure convergence of the proposed DF-SSQP method.
  arXiv  Detail & Related papers  (2025-10-25T23:51:20Z)
• On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization [57.179679246370114]
  A potential limitation of existing methods is the bias inherent in most perturbation estimators unless a stepsize is proposed.<n>We propose a novel family of unbiased gradient scaling estimators that eliminate bias while maintaining favorable construction.
  arXiv  Detail & Related papers  (2025-10-22T18:25:43Z)
• Stochastic Optimization with Optimal Importance Sampling [49.484190237840714]
  We propose an iterative-based algorithm that jointly updates the decision and the IS distribution without requiring time-scale separation between the two.<n>Our method achieves the lowest possible variable variance and guarantees global convergence under convexity of the objective and mild assumptions on the IS distribution family.
  arXiv  Detail & Related papers  (2025-04-04T16:10:18Z)
• Debiased Nonparametric Regression for Statistical Inference and Distributionally Robustness [10.470114319701576]
  We introduce a model-free debiasing method for smooth nonparametric regression estimators.<n>We obtain a debiased estimator that satisfies pointwise and uniform risk convergence, along with smoothness, under mild conditions.
  arXiv  Detail & Related papers  (2024-12-28T15:01:19Z)
• Statistical Inference for Temporal Difference Learning with Linear Function Approximation [55.80276145563105]
  We investigate the statistical properties of Temporal Difference learning with Polyak-Ruppert averaging.<n>We make three theoretical contributions that improve upon the current state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-21T15:34:44Z)
• Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent [43.097493761380186]
  gradient algorithms are an efficient method of approximately solving linear systems. We show that gradient descent produces accurate predictions, even in cases where it does not converge quickly to the optimum. Experimentally, gradient descent achieves state-of-the-art performance on sufficiently large-scale or ill-conditioned regression tasks.
  arXiv  Detail & Related papers  (2023-06-20T15:07:37Z)
• Semi-Parametric Inference for Doubly Stochastic Spatial Point Processes: An Approximate Penalized Poisson Likelihood Approach [3.085995273374333]
  Doubly-stochastic point processes model the occurrence of events over a spatial domain as an inhomogeneous process conditioned on the realization of a random intensity function. Existing implementations of doubly-stochastic spatial models are computationally demanding, often have limited theoretical guarantee, and/or rely on restrictive assumptions.
  arXiv  Detail & Related papers  (2023-06-11T19:48:39Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods [8.890430804063705]
  We first present the distribution for the Polyak-Ruppert-averaging type Kiefer-Wolfowitz (AKW) estimators. The distributional result reflects the trade-off between statistical efficiency and function query complexity.
  arXiv  Detail & Related papers  (2021-02-05T19:22:41Z)
• ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm [71.13558000599839]
  We study the problem of solving strongly convex and smooth unconstrained optimization problems using first-order algorithms. We devise a novel, referred to as Recursive One-Over-T SGD, based on an easily implementable, averaging of past gradients. We prove that it simultaneously achieves state-of-the-art performance in both a finite-sample, nonasymptotic sense and an sense.
  arXiv  Detail & Related papers  (2020-08-28T14:46:56Z)
• Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent [55.85456985750134]
  We introduce a new stability measure called on-average model stability, for which we develop novel bounds controlled by the risks of SGD iterates. This yields generalization bounds depending on the behavior of the best model, and leads to the first-ever-known fast bounds in the low-noise setting. To our best knowledge, this gives the firstever-known stability and generalization for SGD with even non-differentiable loss functions.
  arXiv  Detail & Related papers  (2020-06-15T06:30:19Z)
• Instability, Computational Efficiency and Statistical Accuracy [101.32305022521024]
  We develop a framework that yields statistical accuracy based on interplay between the deterministic convergence rate of the algorithm at the population level, and its degree of (instability) when applied to an empirical object based on $n$ samples. We provide applications of our general results to several concrete classes of models, including Gaussian mixture estimation, non-linear regression models, and informative non-response models.
  arXiv  Detail & Related papers  (2020-05-22T22:30:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.