Convergence Conditions of Online Regularized Statistical Learning in Reproducing Kernel Hilbert Space With Non-Stationary Data

• URL: http://arxiv.org/abs/2404.03211v4
• Date: Sun, 9 Jun 2024 13:11:36 GMT
• Title: Convergence Conditions of Online Regularized Statistical Learning in Reproducing Kernel Hilbert Space With Non-Stationary Data
• Authors: Xiwei Zhang, Tao Li,
• Abstract summary: We study the convergence of regularized learning algorithms in the reproducing kernel HilbertRKHS with dependent and non-stationary online data streams. For independent and non-identically distributed data streams, the algorithm achieves the mean square consistency.
• Score: 4.5692679976952215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the convergence of recursive regularized learning algorithms in the reproducing kernel Hilbert space (RKHS) with dependent and non-stationary online data streams. Firstly, we study the mean square asymptotic stability of a class of random difference equations in RKHS, whose non-homogeneous terms are martingale difference sequences dependent on the homogeneous ones. Secondly, we introduce the concept of random Tikhonov regularization path, and show that if the regularization path is slowly time-varying in some sense, then the output of the algorithm is consistent with the regularization path in mean square. Furthermore, if the data streams also satisfy the RKHS persistence of excitation condition, i.e. there exists a fixed length of time period, such that the conditional expectation of the operators induced by the input data accumulated over every time period has a uniformly strictly positive compact lower bound in the sense of the operator order with respect to time, then the output of the algorithm is consistent with the unknown function in mean square. Finally, for the case with independent and non-identically distributed data streams, the algorithm achieves the mean square consistency provided the marginal probability measures induced by the input data are slowly time-varying and the average measure over each fixed-length time period has a uniformly strictly positive lower bound.

Related papers

• Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems [78.96969465641024]
  We extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We also study time and particle discretization regimes and prove a new uniform-in-time propagation of chaos result.
  arXiv  Detail & Related papers  (2023-12-02T13:01:29Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Random Inverse Problems Over Graphs: Decentralized Online Learning [4.5692679976952215]
  We establish a framework of distributed random inverse problems over network graphs with online measurements. We develop the L2 -asymptotic stability theory in the infinite Hilbert spaces. We propose a decentralized online learning algorithm in RKHS based on non-stationary and non-independent online data.
  arXiv  Detail & Related papers  (2023-03-20T08:37:08Z)
• Boosting the Confidence of Generalization for $L_2$-Stable Randomized Learning Algorithms [41.082982732100696]
  We show that a properly designed subbagging process leads to near-tight exponential generalization bounds over both data and algorithm. We further derive generic results to improve high-probability generalization bounds for convex or non-tight problems with natural decaying learning rates.
  arXiv  Detail & Related papers  (2022-06-08T12:14:01Z)
• Decentralized Online Regularized Learning Over Random Time-Varying Graphs [4.065547532041163]
  We develop the online regularized linear regression algorithm over random time-varying graphs. We prove that the regret upper bound is $O(T1-tauln T)$, where $tauin (0.5,1)$ is a constant depending on the algorithm gains. In addition, we prove that the regret upper bound is $O(T1-tauln T)$, where $tauin (0.5,1)$ is a constant depending on the algorithm gains.
  arXiv  Detail & Related papers  (2022-06-07T12:55:08Z)
• Spatio-Temporal Variational Gaussian Processes [26.60276485130467]
  We introduce a scalable approach to Gaussian process inference that combinestemporal-temporal filtering with natural variational inference. We derive a sparse approximation that constructs a state-space model over a reduced set of inducing points. We show that for separable Markov kernels the full sparse cases recover exactly the standard variational GP.
  arXiv  Detail & Related papers  (2021-11-02T16:53:31Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• The Connection between Discrete- and Continuous-Time Descriptions of Gaussian Continuous Processes [60.35125735474386]
  We show that discretizations yielding consistent estimators have the property of invariance under coarse-graining' This result explains why combining differencing schemes for derivatives reconstruction and local-in-time inference approaches does not work for time series analysis of second or higher order differential equations.
  arXiv  Detail & Related papers  (2021-01-16T17:11:02Z)

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.