A Stability Principle for Learning under Non-Stationarity

• URL: http://arxiv.org/abs/2310.18304v5
• Date: Fri, 16 May 2025 15:26:15 GMT
• Title: A Stability Principle for Learning under Non-Stationarity
• Authors: Chengpiao Huang, Kaizheng Wang,
• Abstract summary: We develop a versatile framework for statistical learning in non-stationary environments.<n>We prove regret bounds that are minimax optimal up to logarithmic factors when the population losses are strongly convex, or Lipschitz only.<n>We evaluate the practical performance of our approach through real-data experiments on electricity demand prediction and hospital nurse staffing.
• Score: 1.1510009152620668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop a versatile framework for statistical learning in non-stationary environments. In each time period, our approach applies a stability principle to select a look-back window that maximizes the utilization of historical data while keeping the cumulative bias within an acceptable range relative to the stochastic error. Our theory showcases the adaptivity of this approach to unknown non-stationarity. We prove regret bounds that are minimax optimal up to logarithmic factors when the population losses are strongly convex, or Lipschitz only. At the heart of our analysis lie two novel components: a measure of similarity between functions and a segmentation technique for dividing the non-stationary data sequence into quasi-stationary pieces. We evaluate the practical performance of our approach through real-data experiments on electricity demand prediction and hospital nurse staffing.

Related papers

• Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs [2.926192989090622]
  We study the estimation of the value function for continuous-time Markov diffusion processes. Our work provides non-asymptotic statistical guarantees for the least-squares temporal-difference method.
  arXiv  Detail & Related papers  (2025-02-06T18:39:03Z)
• Statistical Inference for Temporal Difference Learning with Linear Function Approximation [62.69448336714418]
  Temporal Difference (TD) learning, arguably the most widely used for policy evaluation, serves as a natural framework for this purpose. In this paper, we study the consistency properties of TD learning with Polyak-Ruppert averaging and linear function approximation, and obtain three significant improvements over existing results.
  arXiv  Detail & Related papers  (2024-10-21T15:34:44Z)
• Federated Nonparametric Hypothesis Testing with Differential Privacy Constraints: Optimal Rates and Adaptive Tests [5.3595271893779906]
  Federated learning has attracted significant recent attention due to its applicability across a wide range of settings where data is collected and analyzed across disparate locations. We study federated nonparametric goodness-of-fit testing in the white-noise-with-drift model under distributed differential privacy (DP) constraints.
  arXiv  Detail & Related papers  (2024-06-10T19:25:19Z)
• Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients [0.3277163122167434]
  We show how to formulate a functional gradient descent algorithm to tackle NPIV regression by directly minimizing the populational risk. We provide theoretical support in the form of bounds on the excess risk, and conduct numerical experiments showcasing our method's superior stability and competitive performance. This algorithm enables flexible estimator choices, such as neural networks or kernel based methods, as well as non-quadratic loss functions.
  arXiv  Detail & Related papers  (2024-02-08T12:50:38Z)
• Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization [29.24821214671497]
  Training machine learning and statistical models often involve optimizing a data-driven risk criterion. We propose a novel robust criterion by combining insights from Bayesian nonparametric (i.e., Dirichlet process) theory and a recent decision-theoretic model of smooth ambiguity-averse preferences. For practical implementation, we propose and study tractable approximations of the criterion based on well-known Dirichlet process representations.
  arXiv  Detail & Related papers  (2024-01-28T21:19:15Z)
• Selective Nonparametric Regression via Testing [54.20569354303575]
  We develop an abstention procedure via testing the hypothesis on the value of the conditional variance at a given point. Unlike existing methods, the proposed one allows to account not only for the value of the variance itself but also for the uncertainty of the corresponding variance predictor.
  arXiv  Detail & Related papers  (2023-09-28T13:04:11Z)
• Statistical Estimation Under Distribution Shift: Wasserstein Perturbations and Minimax Theory [24.540342159350015]
  We focus on Wasserstein distribution shifts, where every data point may undergo a slight perturbation. We consider perturbations that are either independent or coordinated joint shifts across data points. We analyze several important statistical problems, including location estimation, linear regression, and non-parametric density estimation.
  arXiv  Detail & Related papers  (2023-08-03T16:19:40Z)
• 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)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• Data-Driven Influence Functions for Optimization-Based Causal Inference [105.5385525290466]
  We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite differencing. We study the case where probability distributions are not known a priori but need to be estimated from data.
  arXiv  Detail & Related papers  (2022-08-29T16:16:22Z)
• A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization With Non-isolated Local Minima [0.0]
  Non-isolated minima presents a unique challenge that has remained under-explored. In this paper, we study the local convergence of the gradient descent method to non-isolated global minima.
  arXiv  Detail & Related papers  (2022-03-21T13:33:37Z)
• Counterfactual inference in sequential experiments [17.817769460838665]
  We consider after-study statistical inference for sequentially designed experiments wherein multiple units are assigned treatments for multiple time points.<n>Our goal is to provide inference guarantees for the counterfactual mean at the smallest possible scale.<n>We illustrate our theory via several simulations and a case study involving data from a mobile health clinical trial HeartSteps.
  arXiv  Detail & Related papers  (2022-02-14T17:24:27Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Near-optimal inference in adaptive linear regression [60.08422051718195]
  Even simple methods like least squares can exhibit non-normal behavior when data is collected in an adaptive manner. We propose a family of online debiasing estimators to correct these distributional anomalies in at least squares estimation. We demonstrate the usefulness of our theory via applications to multi-armed bandit, autoregressive time series estimation, and active learning with exploration.
  arXiv  Detail & Related papers  (2021-07-05T21:05:11Z)
• Learning Prediction Intervals for Regression: Generalization and Calibration [12.576284277353606]
  We study the generation of prediction intervals in regression for uncertainty quantification. We use a general learning theory to characterize the optimality-feasibility tradeoff that encompasses Lipschitz continuity and VC-subgraph classes. We empirically demonstrate the strengths of our interval generation and calibration algorithms in terms of testing performances compared to existing benchmarks.
  arXiv  Detail & Related papers  (2021-02-26T17:55:30Z)
• Nonlinear Independent Component Analysis for Continuous-Time Signals [85.59763606620938]
  We study the classical problem of recovering a multidimensional source process from observations of mixtures of this process. We show that this recovery is possible for many popular models of processes (up to order and monotone scaling of their coordinates) if the mixture is given by a sufficiently differentiable, invertible function.
  arXiv  Detail & Related papers  (2021-02-04T20:28:44Z)
• CoinDICE: Off-Policy Confidence Interval Estimation [107.86876722777535]
  We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning. We show in a variety of benchmarks that the confidence interval estimates are tighter and more accurate than existing methods.
  arXiv  Detail & Related papers  (2020-10-22T12:39:11Z)
• A Stochastic Subgradient Method for Distributionally Robust Non-Convex Learning [2.007262412327553]
  robustness is with respect to uncertainty in the underlying data distribution. We show that our technique converges to satisfying perturbationity conditions. We also illustrate the performance of our algorithm on real datasets.
  arXiv  Detail & Related papers  (2020-06-08T18:52:40Z)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)

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.