Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

19385776 · Nov 201919922001200920182026
48 results for State-space filtering

A new method learns state and proposal dynamics in state-space models using neural networks.

problem Inference in non-linear state-space models.
method StateMixNN method using neural networks for proposal and transition distributions.
result Significantly improved recovery of hidden state, especially in highly non-linear scenarios.

A new method for state space partitioning in block particle filtering reduces bias and variance.

problem Overcoming the curse of dimensionality in non-linear, non-Gaussian state space estimation.
method Formulates state space partitioning as a clustering problem and uses spectral clustering with constraints.
result The proposed method effectively groups correlated state variables into smaller blocks, reducing bias and variance.

The paper analyzes a recursive ML estimation method for non-linear state-space models.

problem Estimating maxima of the log-likelihood function in non-linear state-space models.
method Recursive maximum likelihood estimation using particle approximation to the optimal filter derivative.
result The algorithm accurately estimates maxima of the log-likelihood when the number of particles is sufficiently large.

Improved state estimation in high-dimensional models using Zig-Zag Sampler.

problem Weight degeneracy in particle filtering methods for high-dimensional state space models.
method Discrete Zig-Zag Sampler applied within the Composite MH Kernel of SMCMC framework.
result Improves estimation accuracy and increases acceptance ratio in high-dimensional state estimation.

DVBF learns state space models from raw data without supervision.

problem Unsupervised learning of latent Markovian state space models from raw data.
method Stochastic Gradient Variational Bayes for variational inference.
result DVBF enables realistic long-term prediction and improves latent embedding information content.

Efficient GP models with non-Gaussian likelihoods using state space methods.

problem Modeling non-Gaussian likelihoods in Gaussian Process (GP) regression.
method State space formulation for efficient GP models, combining LA, VB, ADF, and EP schemes.
result Efficient inference methods for non-Gaussian likelihoods in GP models.

IBPF algorithm tackles high-dimensional parameter learning for complex systems.

problem Learning high-dimensional parameters in complex, partially observed, and nonlinear systems.
method Iterated Block Particle Filter (IBPF) for graphical state space models.
result IBPF algorithm consistently beats the curse of dimensionality across various experiments.

Generative Bayesian Filtering improves inference in complex models without explicit density evaluations.

problem Performing posterior inference in complex nonlinear and non-Gaussian state-space models.
method Generative Bayesian Filtering (GBF) extends GBC to dynamic settings using deep neural networks for recursive posterior inference. Generative-Gibbs sampler bypasses density evaluations for parameter learning.
result GBF significantly outperforms likelihood-free approaches in accuracy and robustness for intractable state-space models.

Particle MCMC is a class of algorithms that can be used to analyse state-space models. They use MCMC moves to update the parameters of the models, and particle filters to propose values for the path of the state-space model. Currently the default is to use random walk Metropolis to update the parameter values. We show …

2014-02-04abs ↗pdf ↗

Online learning improves state estimation of nonlinear systems.

problem Online learning of nonlinear state dynamics in Gaussian state space models.
method Stochastic variational sparse Gaussian process embedded in a particle filter framework, with model updating using stochastic gradient descent.
result State estimation performance significantly improves with online learning of state dynamics.

A new particle filter avoids resampling to improve state estimation in high dimensions.

problem Particle deprivation in high-dimensional state spaces.
method A resampling-free particle filter designed to mitigate particle deprivation.
result The filter offers a near-accurate representation of the posterior distribution in high-dimensional contexts.

Paper introduces IO-NPF for efficient Bayesian experimental design.

problem Efficient Bayesian experimental design in non-exchangeable settings.
method Inside-Out Nested Particle Filter (IO-NPF) for non-Markovian state-space models.
result IO-NPF achieves O(T2)\mathcal{O}(T^2) computational complexity, improving efficiency.

The paper stabilizes PD term structures under forecast uncertainty using a Kalman filter with an anchored observation model.

problem Stable estimation of lifetime PDs under forecast uncertainty.
method Reformulated in state-space framework, introduced an anchored observation model.
result Asymptotic stochastic stability of error dynamics, leading to smoother projections.

The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested sets of variables, the DPF uses a particle filter to sample the first set and then conditions on this sample to generate a set of samples for…

2012-03-12abs ↗pdf ↗

In nonlinear state-space models, sequential learning about the hidden state can proceed by particle filtering when the density of the observation conditional on the state is available analytically (e.g. Gordon et al., 1993). This condition need not hold in complex environments, such as the incomplete-information equili…

2011-05-23abs ↗pdf ↗

Study uses a bivariate model to price crude oil futures.

problem Pricing crude oil futures using latent factors and state-space models.
method Modelled short and long term factors as OU processes, estimated using Kalman Filter and maximised Gaussian likelihood.
result Successfully estimated model parameters and factors from WTI Crude Oil NYMEX futures data.

A new method for state estimation in state-space models using incomplete data.

problem State estimation in nonlinear state-space models with incomplete observations.
method Statistical analysis of incomplete observations, score function, observed information matrices, EM-gradient-particle filtering.
result Maximum likelihood estimation of state-vector with explicit form of observed information matrix.

A DRL framework optimizes portfolios using a LFSS module for feature extraction.

problem Optimizing dynamic portfolios in financial markets.
method Deep Reinforcement Learning with a Latent Feature State Space module.
result The proposed DRL framework outperforms benchmarks in portfolio optimization.

Bayesian filtering approach identifies nonlinear restoring forces in dynamic systems.

problem Identification of nonlinear dynamic systems in engineering.
method Modeling the nonlinear restoring force as a Gaussian process, converting it to a state-space model, and inferring internal states and the nonlinear restoring force through filtering and smoothing.
result The approach effectively identifies nonlinear restoring forces in both simulated and experimental datasets.

Develops efficient methods for state-space models with singular errors.

problem Estimating state-space models with singular error covariances.
method Reformulates state-space models as constrained convex optimization problems and develops an efficient algorithm.
result The new approach outperforms competing methods for nonsingular models and is a default choice for state space models.

Many nonlinear extensions of the Kalman filter, e.g., the extended and the unscented Kalman filter, reduce the state densities to Gaussian densities. This approximation gives sufficient results in many cases. However, this filters only estimate states that are correlated with the observation. Therefore, sequential esti…

2012-07-18abs ↗pdf ↗

Paper develops unbiased gradient estimator for continuous-time models.

problem Estimating unbiased gradient of log-likelihood for continuous-time models.
method Doubly randomized scheme with coupled conditional particle filter (CCPF).
result Unbiased gradient estimate facilitates gradient-based algorithms.

New method improves state-space model learning with highly informative observations.

problem Challenges in learning state-space models with little measurement noise.
method Tempered Sequential Monte Carlo (SMC) algorithm to handle highly informative observations.
result Successfully estimates likelihood function for state-space models with minimal measurement noise.

KalMamba improves RL efficiency with probabilistic SSMs.

problem Efficiency in learning and inference for probabilistic SSMs in RL.
method Combines Mamba's scalability with Kalman filtering for efficient probabilistic SSMs.
result KalMamba outperforms state-of-the-art SSMs in RL, especially on longer sequences.

A new filter efficiently samples high-dimensional state spaces using mappings embedded in a reproducing kernel Hilbert space.

problem Efficiently sampling high-dimensional state spaces with limited particles.
method Variational mapping particle filter using gradient flow of mappings embedded in a reproducing kernel Hilbert space.
result Quick convergence and stable performance in various chaotic and epidemic models.

A new method for estimating adversarial strategies in nonlinear systems.

problem Inferring an intelligent adversarial agent's strategy in highly nonlinear systems.
method Formulated inverse cognition as a nonlinear Gaussian state-space model and developed an inverse UKF (IUKF) system.
result The estimation error of IUKF converges and closely follows the recursive Cramér-Rao lower bound.

We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the mean Bellman residual. Our algorithm uses a Kalman filter model to estimate those …

2013-09-26abs ↗pdf ↗

The paper develops a state-space approach to deep Gaussian processes for efficient state estimation.

problem Efficient regression and state estimation for deep Gaussian processes.
method Hierarchical transformed Gaussian process priors, state-space representation, linear stochastic differential equations, sequential methods.
result The state-space approach enables efficient state estimation and regression for deep Gaussian processes.

Paper develops efficient recursive learning for multi-channel systems with heterogeneous dynamics.

problem Accurately learning system dynamics in complex, multi-channel systems with nonlinear and noisy data.
method Formulates system as Gaussian process state-space models (GPSSMs), introduces heterogeneous multi-output kernel, and develops recursive inference framework.
result Matches SOTA offline GPSSMs in accuracy with 1/100 runtime, and outperforms SOTA online GPSSMs by 70% in accuracy under noise with 1/20 runtime.

A new method for Gaussian filtering using gradient flows and Wasserstein metrics.

problem Approximating Gaussian and mixture-of-Gaussians filtering for complex systems.
method Variational approximation via gradient-flow representation on Wasserstein metric space.
result Competitive performance in posterior representation and parameter estimation for systems with multiplicative noise and multi-modal distributions.

RNF learns distinct representations for Bayesian filtering steps, improving time series prediction accuracy and uncertainty.

problem Improving time series prediction accuracy and uncertainty using distinct representations for Bayesian filtering steps.
method Introduces Recurrent Neural Filter (RNF) architecture that learns distinct representations for each Bayesian filtering step.
result RNF improves accuracy of one-step-ahead forecasts and provides realistic uncertainty estimates.

NSIBF detects anomalies in CPS using neural system identification and Bayesian filtering.

problem Detecting anomalies in CPS with complex dynamics and sensor noise.
method Neural System Identification and Bayesian Filtering (NSIBF).
result NSIBF outperforms state-of-the-art methods in anomaly detection for CPS.

The kernel least mean squares (KLMS) algorithm is a computationally efficient nonlinear adaptive filtering method that "kernelizes" the celebrated (linear) least mean squares algorithm. We demonstrate that the least mean squares algorithm is closely related to the Kalman filtering, and thus, the KLMS can be interpreted…

2013-10-20abs ↗pdf ↗

A novel method uses GPLFMs for joint input-state estimation in linear structural systems.

problem Combined state and input estimation of linear structural systems.
method Gaussian process latent force models (GPLFMs) combined with Kalman filters.
result GPLFMs outperform conventional Kalman filters in state and input estimation.