Stability and performance guarantees for misspecified multivariate score-driven filters

• URL: http://arxiv.org/abs/2502.05021v5
• Date: Sat, 27 Sep 2025 12:02:19 GMT
• Title: Stability and performance guarantees for misspecified multivariate score-driven filters
• Abstract summary: We examine score-driven (ISD and ESD) filters, which update parameter predictions using the gradient of the logarithmic postulated observation density.<n>For both filter types, we derive novel sufficient conditions that ensure the exponential stability of the filtered parameter path.<n>We validate our theoretical findings through simulation studies, showing that ISD filters outperform ESD filters in terms of accuracy and stability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can stochastic gradient methods track a moving target? We address the problem of tracking multivariate time-varying parameters under noisy observations and potential model misspecification. Specifically, we examine implicit and explicit score-driven (ISD and ESD) filters, which update parameter predictions using the gradient of the logarithmic postulated observation density (commonly referred to as the score). For both filter types, we derive novel sufficient conditions that ensure the exponential stability of the filtered parameter path and the existence of a finite mean squared error (MSE) bound relative to the pseudo-true parameter path. Our (non-)asymptotic MSE bounds rely on mild moment conditions on the data-generating process, while our stability results are agnostic about the true process. For the ISD filter, concavity of the postulated log density combined with simple parameter restrictions is sufficient to guarantee stability. In contrast, the ESD filter additionally requires the score to be Lipschitz continuous and the learning rate to be sufficiently small. We validate our theoretical findings through simulation studies, showing that ISD filters outperform ESD filters in terms of accuracy and stability.

Related papers

• Ensemble Controlled-Flow Filtering for Implicit Data Assimilation [11.531404987674378]
  We introduce implicit data assimilation, in which the analysis law is defined as an energy tilt of the forecast distribution.<n>We then propose the Ensemble Controlled-flow Filter (EnCF), which realizes this update through a controlled flow.<n>For simulator-defined observations, EnCF-LF learns a surrogate conditional energy from samples and applies the same controlled-flow solver.
  arXiv  Detail & Related papers  (2026-07-14T17:16:37Z)
• Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Decision-Making [0.0]
  We introduce Finite Reliability Representations (FRR), a framework for covering belief spaces by reliability cells.<n>FRR is formulated on beliefs rather than states and uses a cover rather than an equivalence quotient.<n>It applies to finite POMDPs, linear-Gaussian filters, locally linearized nonlinear filters, and particle-filter implementations.
  arXiv  Detail & Related papers  (2026-07-04T20:30:48Z)
• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty [5.4872967954342675]
  Risk-sensitive POMDPs use particle-filter beliefs that scale poorly, obstruct gradient-based optimization, and estimate Conditional Value-at-Risk.<n>We instead formulate grasp acquisition as variational inference over latent contact parameters and object pose, representing the belief with a differentiable Gaussian mixture.
  arXiv  Detail & Related papers  (2026-04-28T17:40:49Z)
• Robust Unscented Kalman Filtering via Recurrent Meta-Adaptation of Sigma-Point Weights [0.0]
  This work introduces the Meta-Adaptive UKF (MA-UKF), a framework that reformulates sigma-point weight as a hyper parameter optimization problem.<n>Unlike standard adaptive filters that rely on instantaneous corrections, our approach employs a Recurrent Context to compress the history of measurement innovations into a compact latent embedding.<n> Numerical benchmarks on maneuvering targets demonstrate that the MA-UKF significantly outperforms standard baselines.
  arXiv  Detail & Related papers  (2026-03-04T18:27:59Z)
• Assumed Density Filtering and Smoothing with Neural Network Surrogate Models [0.0]
  We show that cross entropy is a more appropriate performance metric than RMSE for evaluating the accuracy of filter and smoothers.<n>We demonstrate the superiority of our method for state estimation on a Lorenz system and a Wiener system, and find that our method enables more optimal linear regulation when the state estimate is used for feedback.
  arXiv  Detail & Related papers  (2025-11-12T06:08:53Z)
• Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting [3.5808917363708743]
  M-FISHER is a method for sequential distribution shift detection and stable adaptation in streaming data.<n>For detection, we construct an exponential martingale from non-conformity scores and apply Ville's inequality to obtain time-uniform guarantees on false alarm control.<n>For adaptation, we show that Fisher-preconditioned updates of prompt parameters implement natural gradient descent on the distributional manifold.
  arXiv  Detail & Related papers  (2025-10-04T15:31:26Z)
• A Sample Efficient Conditional Independence Test in the Presence of Discretization [54.047334792855345]
  Conditional Independence (CI) tests directly to discretized data can lead to incorrect conclusions.<n>Recent advancements have sought to infer the correct CI relationship between the latent variables through binarizing observed data.<n>Motivated by this, this paper introduces a sample-efficient CI test that does not rely on the binarization process.
  arXiv  Detail & Related papers  (2025-06-10T12:41:26Z)
• 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. 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)
• 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)
• Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation [91.83820250747935]
  Pseudo-label noise is mainly contained in unstable samples in which predictions of most pixels undergo significant variations during self-training. We introduce the Stable Neighbor Denoising (SND) approach, which effectively discovers highly correlated stable and unstable samples. SND consistently outperforms state-of-the-art methods in various SFUDA semantic segmentation settings.
  arXiv  Detail & Related papers  (2024-06-10T21:44:52Z)
• High Rank Path Development: an approach of learning the filtration of stochastic processes [6.245824251614165]
  We introduce a novel metric called High Rank PCF Distance (HRPCFD) for extended weak convergence. We then show that such HRPCFD admits many favourable analytic properties which allows us to design an efficient algorithm for training HRPCFD from data and construct the HRPCF-GAN. Our numerical experiments on both hypothesis testing and generative modelling validate the out-performance of our approach compared with several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-23T13:20:47Z)
• Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes [44.974100402600165]
  We study the evaluation of a policy best-parametric and worst-case perturbations to a decision process (MDP) We use transition observations from the original MDP, whether they are generated under the same or a different policy. Our estimator is also estimated statistical inference using Wald confidence intervals.
  arXiv  Detail & Related papers  (2024-03-29T18:11:49Z)
• Integrated path stability selection [5.263910852465186]
  We introduce a novel approach to stability selection based on integrating stability paths rather than maximizing over them. This yields upper bounds on E(FP) that are orders of magnitude stronger than previous bounds, leading to significantly more true positives in practice for the same target E(FP) We demonstrate the method on simulations and real data from prostate and colon cancer studies.
  arXiv  Detail & Related papers  (2024-03-23T15:55:52Z)
• Closed-form Filtering for Non-linear Systems [83.91296397912218]
  We propose a new class of filters based on Gaussian PSD Models, which offer several advantages in terms of density approximation and computational efficiency. We show that filtering can be efficiently performed in closed form when transitions and observations are Gaussian PSD Models. Our proposed estimator enjoys strong theoretical guarantees, with estimation error that depends on the quality of the approximation and is adaptive to the regularity of the transition probabilities.
  arXiv  Detail & Related papers  (2024-02-15T08:51:49Z)
• Joint State Estimation and Noise Identification Based on Variational Optimization [8.536356569523127]
  A novel adaptive Kalman filter method based on conjugate-computation variational inference, referred to as CVIAKF, is proposed. The effectiveness of CVIAKF is validated through synthetic and real-world datasets of maneuvering target tracking.
  arXiv  Detail & Related papers  (2023-12-15T07:47:03Z)
• Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach [62.000948039914135]
  Using Differentially Private Gradient Descent with Gradient Clipping (DPSGD-GC) to ensure Differential Privacy (DP) comes at the cost of model performance degradation. We propose a new error-feedback (EF) DP algorithm as an alternative to DPSGD-GC. We establish an algorithm-specific DP analysis for our proposed algorithm, providing privacy guarantees based on R'enyi DP.
  arXiv  Detail & Related papers  (2023-11-24T17:56:44Z)
• Exact Mean Square Linear Stability Analysis for SGD [28.65663421598186]
  We provide an explicit condition on the step size that is both necessary and sufficient for linear stability of gradient descent (SGD) We show that SGD's stability threshold is equivalent to that of a mixture process which takes in each a full batch gradient step w.p. $1-p$, and a single sample gradient step w.p. $p$.
  arXiv  Detail & Related papers  (2023-06-13T15:29:23Z)
• Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty [68.00748155945047]
  Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. Our contribution is a novel abstraction-based controller method for continuous-state models with noise, uncertain parameters, and external disturbances.
  arXiv  Detail & Related papers  (2022-10-12T07:57:03Z)
• Stability of Aggregation Graph Neural Networks [153.70485149740608]
  We study the stability properties of aggregation graph neural networks (Agg-GNNs) considering perturbations of the underlying graph. We prove that the stability bounds are defined by the properties of the filters in the first layer of the CNN that acts on each node. We also conclude that in Agg-GNNs the selectivity of the mapping operators is tied to the properties of the filters only in the first layer of the CNN stage.
  arXiv  Detail & Related papers  (2022-07-08T03:54:52Z)
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise [59.47042225257565]
  We present a novel planning method that does not rely on any explicit representation of the noise distributions. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP)
  arXiv  Detail & Related papers  (2021-10-25T06:18:55Z)
• Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes [11.277354787690646]
  We introduce a family of higher order kernel mean embeddings that generalizes the notion of KME. We derive empirical estimators for the associated higher order maximum mean discrepancies (MMDs) and prove consistency. We construct a family of universal kernels on processes that allows to solve real-world calibration and optimal stopping problems.
  arXiv  Detail & Related papers  (2021-09-08T12:27:25Z)
• Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions [73.33133942934018]
  2D filter parametrization technique plays an important role when designing equivariant convolutions. New equivariant convolution method based on the proposed filter parametrization method, named F-Conv. F-Conv evidently outperforms previous filter parametrization based method in image super-resolution task.
  arXiv  Detail & Related papers  (2021-07-30T10:01:52Z)
• 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)
• Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence [66.83161885378192]
  Area under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for evaluating classification performance for imbalanced problems. We propose a technical method to optimize AUPRC for deep learning.
  arXiv  Detail & Related papers  (2021-04-18T06:22:21Z)
• Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability [0.0]
  For POMDPs, we provide the convergence of a Q learning algorithm for control policies using a finite history of past observations and control actions. We present explicit error bounds relating the approximation error to the length of the finite history window. We show that the limit fixed point equation gives an optimal solution for an approximate belief-MDP.
  arXiv  Detail & Related papers  (2021-03-22T20:14:26Z)
• On Matched Filtering for Statistical Change Point Detection [13.64446865914411]
  Non-parametric randomness and distribution-free two-sample tests have been the foundation of many change point detection algorithms. We address these issues by deriving and applying filters matched to the expected temporal signatures of a change. Our method allows for the localization of change points without the use of ad-hoc post-processing.
  arXiv  Detail & Related papers  (2020-06-09T22:45:58Z)

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.