A weak convergence approach to large deviations for stochastic approximations

• URL: http://arxiv.org/abs/2502.02529v1
• Date: Tue, 04 Feb 2025 17:50:30 GMT
• Title: A weak convergence approach to large deviations for stochastic approximations
• Authors: Henrik Hult, Adam Lindhe, Pierre Nyquist, Guo-Jhen Wu,
• Abstract summary: We prove a large deviation principle for general approximations with state-dependent Markovian noise and decreasing step size. Examples of learning algorithms that are covered include gradient descent, persistent contrastive divergence and the Wang-Landau algorithm.
• Score: 0.9374652839580183
• License:
• Abstract: The theory of stochastic approximations form the theoretical foundation for studying convergence properties of many popular recursive learning algorithms in statistics, machine learning and statistical physics. Large deviations for stochastic approximations provide asymptotic estimates of the probability that the learning algorithm deviates from its expected path, given by a limit ODE, and the large deviation rate function gives insights to the most likely way that such deviations occur. In this paper we prove a large deviation principle for general stochastic approximations with state-dependent Markovian noise and decreasing step size. Using the weak convergence approach to large deviations, we generalize previous results for stochastic approximations and identify the appropriate scaling sequence for the large deviation principle. We also give a new representation for the rate function, in which the rate function is expressed as an action functional involving the family of Markov transition kernels. Examples of learning algorithms that are covered by the large deviation principle include stochastic gradient descent, persistent contrastive divergence and the Wang-Landau algorithm.

Related papers

• In-Context Parametric Inference: Point or Distribution Estimators? [66.22308335324239]
  We show that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems. Our experiments indicate that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems.
  arXiv  Detail & Related papers  (2025-02-17T10:00:24Z)
• Quantitative Error Bounds for Scaling Limits of Stochastic Iterative Algorithms [10.022615790746466]
  We derive non-asymptotic functional approximation error bounds between the algorithm sample paths and the Ornstein-Uhlenbeck approximation. We use our main result to construct error bounds in terms of two common metrics: the L'evy-Prokhorov and bounded Wasserstein distances.
  arXiv  Detail & Related papers  (2025-01-21T15:29:11Z)
• Likelihood approximations via Gaussian approximate inference [3.4991031406102238]
  We propose efficient schemes to approximate the effects of non-Gaussian likelihoods by Gaussian densities. Our results attain good approximation quality for binary and multiclass classification in large-scale point-estimate and distributional inferential settings. As a by-product, we show that the proposed approximate log-likelihoods are a superior alternative to least-squares on raw labels for neural network classification.
  arXiv  Detail & Related papers  (2024-10-28T05:39:26Z)
• The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise [17.493808856903303]
  One fundamental challenge in analyzing an approximation algorithm is to establish its stability. We extend the celebrated Borkar-Meyn theorem for stability bounded from the Martingale difference noise setting to the Markovian noise setting.
  arXiv  Detail & Related papers  (2024-01-15T17:20:17Z)
• Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence [65.63201894457404]
  We propose a novel non-parametric learning paradigm for the identification of drift and diffusion coefficients of non-linear differential equations. The key idea essentially consists of fitting a RKHS-based approximation of the corresponding Fokker-Planck equation to such observations.
  arXiv  Detail & Related papers  (2023-05-24T20:43:47Z)
• Robust empirical risk minimization via Newton's method [9.797319790710711]
  A new variant of Newton's method for empirical risk minimization is studied. The gradient and Hessian of the objective function are replaced by robust estimators. An algorithm for obtaining robust Newton directions based on the conjugate gradient method is also proposed.
  arXiv  Detail & Related papers  (2023-01-30T18:54:54Z)
• Posterior and Computational Uncertainty in Gaussian Processes [52.26904059556759]
  Gaussian processes scale prohibitively with the size of the dataset. Many approximation methods have been developed, which inevitably introduce approximation error. This additional source of uncertainty, due to limited computation, is entirely ignored when using the approximate posterior. We develop a new class of methods that provides consistent estimation of the combined uncertainty arising from both the finite number of data observed and the finite amount of computation expended.
  arXiv  Detail & Related papers  (2022-05-30T22:16:25Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• Statistical optimality and stability of tangent transform algorithms in logit models [6.9827388859232045]
  We provide conditions on the data generating process to derive non-asymptotic upper bounds to the risk incurred by the logistical optima. In particular, we establish local variation of the algorithm without any assumptions on the data-generating process. We explore a special case involving a semi-orthogonal design under which a global convergence is obtained.
  arXiv  Detail & Related papers  (2020-10-25T05:15:13Z)

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.